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. 45230
    Prev
    Next
    INDEX
    Explanations

    references to urban planning and transportation infrastructure issues, including congestion, parking, and sustainability

    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
    161
    +0.08
    0.5%
    93
    +0.07
    0.5%
    649
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.08
    0.07
    649
    +0.07
    0.02
    271
    +0.07
    0.04
    Negative Logits
    ista
    -0.54
    edom
    -0.51
    tell
    -0.51
    ochet
    -0.49
    OGR
    -0.49
     Eisen
    -0.48
    adem
    -0.48
    ining
    -0.48
    anguage
    -0.47
    appro
    -0.47
    POSITIVE LOGITS
     congestion
    0.67
     congest
    0.64
    rates
    0.59
     freeway
    0.54
    fill
    0.50
    pots
    0.50
     headaches
    0.50
     rates
    0.49
     bandwidth
    0.49
    rate
    0.49
    Activations Density 9.621%

    No Known Activations