Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 45326
    Prev
    Next
    INDEX
    Explanations

    the Cyrillic alphabet and associated words or phrases

    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
    308
    +0.14
    0.5%
    447
    +0.13
    0.5%
    353
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    744
    +0.14
    0.11
    434
    +0.13
    0.04
    325
    +0.11
    0.09
    Negative Logits
    ikuman
    -1.03
    oola
    -0.92
     è£ıè
    -0.90
    lehem
    -0.82
    20439
    -0.80
    acid
    -0.80
    Sax
    -0.79
    emouth
    -0.76
    drm
    -0.75
    ottesville
    -0.75
    POSITIVE LOGITS
    士
    1.09
    heit
    0.95
    hirt
    0.79
     Revised
    0.76
    utsche
    0.75
     503
    0.75
    aternity
    0.73
    cription
    0.71
    isse
    0.69
    ashtra
    0.69
    Activations Density 22.655%

    No Known Activations