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. 4382
    Prev
    Next
    INDEX
    Explanations

    locations or specific events related to Guatemala

    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
    635
    +0.03
    0.6%
    578
    +0.03
    0.6%
    623
    +0.02
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.03
    0.27
    99
    +0.03
    0.11
    326
    +0.02
    0.24
    Negative Logits
    tics
    -0.20
    nces
    -0.19
    PUT
    -0.18
    lass
    -0.18
    brate
    -0.18
    nit
    -0.17
    enced
    -0.17
    nc
    -0.17
    train
    -0.17
    ciplinary
    -0.17
    POSITIVE LOGITS
     Guatemala
    0.18
     Aires
    0.18
    asper
    0.17
    alan
    0.16
     Arri
    0.16
     Kenobi
    0.16
     Confederation
    0.16
    avorite
    0.15
    arten
    0.15
    adelphia
    0.15
    Activations Density 10.261%

    No Known Activations