© 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. 1042
    Prev
    Next
    INDEX
    Explanations

    terms related to user interface elements and instructions on using software interfaces

    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
    537
    +0.14
    0.6%
    108
    +0.11
    0.4%
    455
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    99
    +0.14
    0.07
    435
    +0.11
    0.05
    607
    +0.11
    0.06
    Negative Logits
    thood
    -1.03
    ocide
    -0.86
    emort
    -0.85
    ensable
    -0.83
    edIn
    -0.82
    iton
    -0.81
    ãĥīãĥ©
    -0.80
    wat
    -0.76
    Os
    -0.75
    onis
    -0.74
    POSITIVE LOGITS
     periphery
    1.06
    most
    1.03
     corner
    0.97
    isphere
    0.89
     square
    0.89
     courtyard
    0.84
     thereof
    0.84
     of
    0.83
     flank
    0.82
     balcony
    0.81
    Activations Density 1.388%

    No Known Activations