© 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. 13161
    Prev
    Next
    INDEX
    Explanations

    phrases related to individuals or groups working together or being in the same situation

    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
    +0.23
    1.0%
    393
    +0.12
    0.5%
    743
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.23
    0.14
    55
    +0.12
    0.17
    393
    +0.11
    0.28
    Negative Logits
    Trend
    -0.92
    antics
    -0.82
    fecture
    -0.78
    ugu
    -0.75
    ĺħ
    -0.72
    hibition
    -0.72
    opian
    -0.70
    ournal
    -0.70
    vernment
    -0.70
    nosis
    -0.69
    POSITIVE LOGITS
     sides
    1.15
     halves
    1.15
     sexes
    0.95
    ocating
    0.82
     equally
    0.81
     genders
    0.80
     fronts
    0.80
    edged
    0.78
     coasts
    0.77
     thirds
    0.75
    Activations Density 11.741%

    No Known Activations