© 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 Local
    9. 6-RES_SCL-AJT
    11. 14261
    Prev
    Next
    INDEX
    Explanations

    interrogative statements

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    447
    +0.22
    0.9%
    55
    +0.16
    0.6%
    393
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    55
    +0.22
    0.20
    102
    +0.16
    0.19
    640
    +0.14
    0.24
    Negative Logits
    hyde
    -0.84
    hedon
    -0.76
    lems
    -0.76
     Dickinson
    -0.75
    heres
    -0.75
    tails
    -0.72
    staking
    -0.71
    pox
    -0.70
    itches
    -0.70
    hens
    -0.69
    POSITIVE LOGITS
     happening
    0.97
    nt
    0.95
    omorphic
    0.89
     meant
    0.86
     actually
    0.82
     supposed
    0.81
     exactly
    0.76
     truly
    0.75
     really
    0.75
     ultimately
    0.75
    Activations Density 11.213%

    No Known Activations