© 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
    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. 4833
    Prev
    Next
    INDEX
    Explanations

    phrases related to vagrancy, politics, and modern social issues

    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
    240
    +0.12
    0.6%
    285
    +0.10
    0.5%
    70
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.22
    326
    +0.10
    0.20
    48
    +0.10
    0.10
    Negative Logits
    acebook
    -0.94
    EStream
    -0.90
    akespe
    -0.81
    ichick
    -0.78
    elaide
    -0.78
    ONSORED
    -0.77
     Flavoring
    -0.73
    oulos
    -0.71
    ombies
    -0.69
    aeda
    -0.69
    POSITIVE LOGITS
    pants
    0.73
    rant
    0.69
     hose
    0.66
    pee
    0.65
     tant
    0.65
    ure
    0.64
     menstru
    0.63
     loader
    0.62
    rogen
    0.62
    glers
    0.62
    Activations Density 6.011%

    No Known Activations