© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 12823
    Prev
    Next
    INDEX
    Explanations

    the word "need"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "need" used in various contexts

    oai_token-act-pair · gpt-3.5-turboTriggered by @danbraun
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    609
    +0.18
    0.6%
    285
    +0.17
    0.6%
    213
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    609
    +0.18
    0.08
    498
    +0.17
    0.07
    285
    +0.14
    0.06
    Negative Logits
     Democr
    -1.03
    washer
    -0.92
    gdala
    -0.91
     Pill
    -0.91
     Guilty
    -0.89
     Glac
    -0.88
    cheat
    -0.83
    dylib
    -0.82
    wikipedia
    -0.81
    bowl
    -0.81
    POSITIVE LOGITS
    lessly
    1.84
    FINE
    1.08
    othes
    1.05
    ache
    1.03
    n
    0.98
     reminding
    0.98
    igslist
    0.97
    ILY
    0.97
     attention
    0.93
     scarce
    0.91
    Activations Density 1.717%

    No Known Activations