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. 45204
    Prev
    Next
    INDEX
    Explanations

    file paths and technical commands

    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
    549
    +0.07
    0.5%
    731
    +0.07
    0.4%
    606
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.07
    0.41
    393
    +0.07
    0.38
    160
    +0.07
    0.27
    Negative Logits
    gerald
    -0.51
    hran
    -0.46
     Bourbon
    -0.42
    ering
    -0.40
     Bye
    -0.40
     Regulation
    -0.40
     Sig
    -0.40
     VIDEOS
    -0.39
     Rodrigo
    -0.39
    ARDS
    -0.39
    POSITIVE LOGITS
    runtime
    0.55
    abase
    0.53
    live
    0.53
    ãĤ»
    0.51
    cas
    0.48
    earth
    0.48
    cache
    0.48
    aneously
    0.48
    ctica
    0.47
    root
    0.45
    Activations Density 17.463%

    No Known Activations