© 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. 39568
    Prev
    Next
    INDEX
    Explanations

    locations or places mentioned in news articles

    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
    211
    +0.08
    0.5%
    402
    +0.07
    0.5%
    535
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.08
    0.22
    288
    +0.07
    0.21
    201
    +0.07
    0.09
    Negative Logits
    matically
    -0.74
    matical
    -0.69
    eon
    -0.58
    ran
    -0.56
    acies
    -0.54
    race
    -0.54
    alis
    -0.53
    matic
    -0.52
    Arthur
    -0.52
     Seym
    -0.51
    POSITIVE LOGITS
     peppers
    0.53
    vernment
    0.50
     pepper
    0.49
     Reno
    0.47
    ocrates
    0.46
    etooth
    0.46
     Mandela
    0.45
     stove
    0.44
    ascus
    0.44
     chic
    0.44
    Activations Density 6.597%

    No Known Activations