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. 34300
    Prev
    Next
    INDEX
    Explanations

    instructions for crafting or assembling items using specific materials and tools

    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
    167
    +0.09
    0.5%
    546
    +0.08
    0.5%
    5
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.09
    0.23
    288
    +0.08
    0.21
    4
    +0.07
    0.10
    Negative Logits
    lean
    -0.60
    clinton
    -0.55
    ¥µ
    -0.54
    renheit
    -0.52
    okemon
    -0.52
    ghai
    -0.52
     Belg
    -0.51
    estial
    -0.50
    leep
    -0.50
     Haram
    -0.50
    POSITIVE LOGITS
     weld
    0.80
    uring
    0.74
    driver
    0.74
    eer
    0.68
     seams
    0.65
     glue
    0.64
     molded
    0.62
     welding
    0.61
     fabrication
    0.61
     sten
    0.60
    Activations Density 9.117%

    No Known Activations