© 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. 33932
    Prev
    Next
    INDEX
    Explanations

    differences and variations in data

    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
    +0.27
    1.1%
    679
    +0.18
    0.8%
    739
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    160
    +0.27
    0.18
    654
    +0.18
    0.07
    640
    +0.15
    0.19
    Negative Logits
    ATA
    -0.85
    rollers
    -0.83
    ãĥİ
    -0.82
    der
    -0.78
    tsky
    -0.75
    ת
    -0.75
    roller
    -0.73
    trak
    -0.71
    stra
    -0.71
    ×Ķ
    -0.70
    POSITIVE LOGITS
     between
    1.09
    ials
    1.03
    between
    1.00
    yip
    0.97
    iveness
    0.96
    ially
    0.96
    iating
    0.95
    iculty
    0.93
    ensable
    0.84
     Between
    0.83
    Activations Density 8.820%

    No Known Activations