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. 45221
    Prev
    Next
    INDEX
    Explanations

    places or organizations related to Baltimore

    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
    447
    +0.12
    0.6%
    288
    +0.12
    0.6%
    527
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.20
    326
    +0.12
    0.17
    401
    +0.11
    0.10
    Negative Logits
    yip
    -0.95
    uador
    -0.94
    mble
    -0.90
    utterstock
    -0.89
    aeda
    -0.80
    atures
    -0.75
    aterasu
    -0.75
    hhhh
    -0.74
    pter
    -0.73
    berman
    -0.73
    POSITIVE LOGITS
     Orioles
    1.19
     Ravens
    1.06
     Wire
    0.89
     Colts
    0.89
     City
    0.80
     Harbor
    0.78
     Hopkins
    0.78
     Yards
    0.72
     County
    0.68
    rawler
    0.68
    Activations Density 5.486%

    No Known Activations