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

    Neuronpedia

    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. 3563
    Prev
    Next
    INDEX
    Explanations

    news articles mentioning the network CBS

    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
    649
    +0.21
    0.6%
    326
    +0.18
    0.6%
    369
    +0.18
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    343
    +0.21
    0.04
    326
    +0.18
    0.04
    369
    +0.18
    0.03
    Negative Logits
    agnar
    -1.43
    Reviewer
    -1.42
    ainer
    -1.36
    afort
    -1.28
    imates
    -1.21
    htaking
    -1.19
    aced
    -1.11
    rha
    -1.10
    oppable
    -1.08
    arist
    -1.07
    POSITIVE LOGITS
    DAQ
    1.38
     Interactive
    1.29
    ANE
    1.29
    IRO
    1.26
     Evening
    1.24
    MET
    1.21
    DF
    1.19
    RC
    1.19
    EW
    1.18
    IS
    1.17
    Activations Density 0.597%

    No Known Activations