© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 4675
    Prev
    Next
    INDEX
    Explanations

    word origins and meanings in various languages

    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
    481
    +0.10
    0.6%
    71
    +0.09
    0.5%
    447
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.10
    0.30
    107
    +0.09
    0.05
    6
    +0.09
    0.15
    Negative Logits
     dope
    -0.68
    espie
    -0.66
     Dill
    -0.66
     Dragonbound
    -0.65
    brance
    -0.60
     McGee
    -0.60
    wagen
    -0.59
    ftime
    -0.59
     PD
    -0.57
     McKenna
    -0.56
    POSITIVE LOGITS
    ŃĶ
    1.01
    ¥ŀ
    1.00
    ķ
    0.99
    ĺ
    0.96
    Ģ
    0.96
    ĥ
    0.96
    Ľ
    0.96
    Ķ
    0.96
    ħ
    0.95
    ı
    0.94
    Activations Density 12.445%

    No Known Activations