© 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. 34876
    Prev
    Next
    INDEX
    Explanations

    references to physical locations like specific places and infrastructure, such as train stations and subway lines

    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
    +0.29
    1.2%
    326
    +0.15
    0.6%
    288
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.29
    0.17
    391
    +0.15
    0.05
    114
    +0.13
    0.07
    Negative Logits
    vernment
    -0.73
     Marketable
    -0.73
    erenn
    -0.72
    STEM
    -0.71
    ojure
    -0.70
    ogle
    -0.70
    IGHTS
    -0.70
    iferation
    -0.69
    ":"/
    -0.68
     nerv
    -0.66
    POSITIVE LOGITS
     wagon
    1.17
     station
    1.05
     stations
    1.01
    wagon
    0.95
    ery
    0.94
     retri
    0.84
     Station
    0.84
    mates
    0.84
    piece
    0.82
    pole
    0.81
    Activations Density 5.492%

    No Known Activations