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. 13305
    Prev
    Next
    INDEX
    Explanations

    references to light bulbs

    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
    326
    +0.08
    0.5%
    195
    +0.06
    0.4%
    569
    +0.06
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.08
    0.21
    30
    +0.06
    0.05
    288
    +0.06
    0.19
    Negative Logits
    SEA
    -0.45
    heid
    -0.45
    ORD
    -0.43
    ificial
    -0.42
    REAM
    -0.42
    ordan
    -0.42
    CB
    -0.41
    arnaev
    -0.40
    DCS
    -0.40
     Vader
    -0.40
    POSITIVE LOGITS
    ascus
    0.67
    ous
    0.59
    bul
    0.59
    orescent
    0.57
     aver
    0.52
     bulbs
    0.52
    ular
    0.52
    ophobia
    0.52
    entary
    0.52
     bulb
    0.51
    Activations Density 7.834%

    No Known Activations