© 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 EvalsExportsinterp-engineNEWAPI 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. 2412
    Prev
    Next
    INDEX
    Explanations

    quotes or dialogue in a text

    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
    360
    +0.16
    0.5%
    105
    +0.13
    0.4%
    184
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    426
    +0.16
    0.04
    205
    +0.13
    0.04
    102
    +0.13
    0.04
    Negative Logits
     cannabin
    -1.17
    azo
    -1.12
     destro
    -1.08
     distribut
    -1.05
    ypes
    -1.05
    £ı
    -1.02
     tradem
    -0.98
     CPS
    -0.98
     mug
    -0.96
    avorite
    -0.92
    POSITIVE LOGITS
    cause
    1.45
    tis
    1.40
    Hey
    1.30
    til
    1.29
    trust
    1.25
    church
    1.23
    Jesus
    1.22
    Why
    1.21
    nothing
    1.21
    why
    1.20
    Activations Density 0.375%

    No Known Activations