© 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. 6678
    Prev
    Next
    INDEX
    Explanations

    adjectives describing the intensity or quantity of something

    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
    245
    +0.18
    0.6%
    493
    +0.14
    0.5%
    408
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    95
    +0.18
    0.04
    252
    +0.14
    0.04
    493
    +0.14
    0.04
    Negative Logits
    İĭ
    -1.37
    etts
    -1.20
    ģĸ
    -1.11
    bors
    -1.11
    bley
    -1.08
    oscope
    -1.07
    reditary
    -1.05
    plets
    -1.04
    ysc
    -1.02
    ĺħ
    -1.01
    POSITIVE LOGITS
     effort
    1.00
     fun
    0.97
     than
    0.93
     bang
    0.89
     ado
    0.89
     appreciated
    0.88
     diverse
    0.87
    antz
    0.87
     faith
    0.87
     trouble
    0.87
    Activations Density 0.269%

    No Known Activations