© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 35275
    Prev
    Next
    INDEX
    Explanations

    cities and places

    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
    +0.28
    1.3%
    288
    +0.11
    0.5%
    752
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    752
    +0.28
    0.13
    442
    +0.11
    0.09
    133
    +0.11
    0.09
    Negative Logits
    vana
    -1.01
    merce
    -0.79
    arist
    -0.75
    arial
    -0.75
    udic
    -0.75
    acca
    -0.73
    rar
    -0.73
    egal
    -0.73
    abet
    -0.70
    rag
    -0.69
    POSITIVE LOGITS
     skyline
    1.00
     Mayor
    0.88
     Heights
    0.84
     Harbor
    0.83
     Airport
    0.80
     suburb
    0.79
     suburbs
    0.79
     Bay
    0.79
     Metropolitan
    0.79
     metro
    0.78
    Activations Density 8.600%

    No Known Activations