© 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. 12800
    Prev
    Next
    INDEX
    Explanations

    references to the state of being 'alive'

    oai_token-act-pair · gpt-3.5-turbo
    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
    132
    +0.22
    0.8%
    288
    +0.19
    0.7%
    223
    +0.16
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.22
    0.09
    132
    +0.19
    0.06
    99
    +0.16
    0.05
    Negative Logits
    pled
    -1.13
    ple
    -1.04
    ples
    -0.92
    ipal
    -0.89
    RECT
    -0.88
    agree
    -0.87
    pling
    -0.86
    med
    -0.85
    soDeliveryDate
    -0.85
    ihad
    -0.84
    POSITIVE LOGITS
     alive
    1.23
    abouts
    1.12
    lihood
    1.06
     Alive
    0.99
    lier
    0.90
    hart
    0.88
    lio
    0.86
    ansas
    0.83
    beat
    0.83
     Parish
    0.83
    Activations Density 0.983%

    No Known Activations