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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 45163
    Prev
    Next
    INDEX
    Explanations

    names of official organizations and titles

    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
    388
    +0.06
    0.4%
    556
    +0.06
    0.4%
    478
    +0.06
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    409
    +0.06
    0.07
    196
    +0.06
    0.05
    652
    +0.06
    0.07
    Negative Logits
    Fair
    -0.46
    mini
    -0.46
    atre
    -0.45
    byn
    -0.42
    rise
    -0.41
     Dwarf
    -0.41
    morrow
    -0.41
    atro
    -0.40
    kun
    -0.40
    colour
    -0.40
    POSITIVE LOGITS
     branches
    0.49
    vernment
    0.49
     Inspect
    0.46
     memo
    0.44
     eaves
    0.44
    asury
    0.44
     branch
    0.44
     counterterrorism
    0.43
     presidents
    0.42
     attorneys
    0.41
    Activations Density 10.866%

    No Known Activations