© 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. 6915
    Prev
    Next
    INDEX
    Explanations

    quantifiers indicating a large amount or degree

    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
    518
    +0.03
    0.5%
    620
    +0.02
    0.4%
    441
    +0.02
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    441
    +0.03
    0.04
    408
    +0.02
    0.05
    355
    +0.02
    0.04
    Negative Logits
    pmwiki
    -0.21
    ngth
    -0.18
    ORTS
    -0.18
     advis
    -0.17
     parallels
    -0.17
    =#
    -0.17
    ptives
    -0.17
    usterity
    -0.16
    kefeller
    -0.16
     shakes
    -0.16
    POSITIVE LOGITS
    efeated
    0.18
    uke
    0.16
    });
    0.16
    enge
    0.16
     Keane
    0.15
     stash
    0.15
    etta
    0.15
     Capcom
    0.15
    aud
    0.15
     Sakura
    0.15
    Activations Density 0.371%

    No Known Activations