© 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. 5026
    Prev
    Next
    INDEX
    Explanations

    information related to military organizations and operations

    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
    +0.24
    1.1%
    32
    +0.11
    0.5%
    679
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.24
    0.19
    732
    +0.11
    0.07
    748
    +0.11
    0.06
    Negative Logits
    stem
    -0.76
    adr
    -0.71
    abies
    -0.71
    atters
    -0.70
    licks
    -0.69
    ugu
    -0.69
    aces
    -0.69
    bane
    -0.68
    aced
    -0.68
    ichen
    -0.68
    POSITIVE LOGITS
     assorted
    0.82
    ++++
    0.76
    minus
    0.75
    cules
    0.71
     append
    0.69
     plus
    0.68
    -+-+-+-+
    0.64
     amen
    0.64
    ï¸
    0.64
    /-
    0.63
    Activations Density 5.830%

    No Known Activations