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

    Neuronpedia

    APICircuit 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. 34619
    Prev
    Next
    INDEX
    Explanations

    locations or events related to the city of Pittsburgh

    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
    420
    +0.16
    0.7%
    447
    +0.13
    0.6%
    679
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.16
    0.27
    326
    +0.13
    0.24
    346
    +0.11
    0.12
    Negative Logits
    abet
    -0.92
    itton
    -0.82
    andise
    -0.81
    APH
    -0.79
    neau
    -0.78
    agall
    -0.78
    pora
    -0.77
    itic
    -0.77
    abetic
    -0.76
    ctica
    -0.75
    POSITIVE LOGITS
    sburgh
    1.18
    erick
    0.90
    er
    0.83
    enthal
    0.80
     hots
    0.78
    enstein
    0.78
     Venom
    0.77
     Steelers
    0.76
     Penguins
    0.74
    ingen
    0.74
    Activations Density 8.450%

    No Known Activations