© 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. 4789
    Prev
    Next
    INDEX
    Explanations

    technical descriptions related to physical processes or objects, particularly those involving machinery or engineering

    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
    +0.15
    0.9%
    304
    +0.10
    0.6%
    716
    +0.09
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.15
    0.03
    486
    +0.10
    0.06
    554
    +0.09
    -0.15
    Negative Logits
    é¾įå¥ij士
    -0.71
    ģĸ
    -0.54
    lik
    -0.54
    Ļ½
    -0.53
    ril
    -0.45
    pires
    -0.44
    emporary
    -0.44
    atever
    -0.43
    roo
    -0.43
    rek
    -0.42
    POSITIVE LOGITS
     themselves
    0.88
     collectively
    0.68
     respective
    0.66
    selves
    0.63
     individually
    0.60
     selves
    0.54
     respectively
    0.53
     arsen
    0.53
     weren
    0.51
     necks
    0.51
    Activations Density 19.859%

    No Known Activations