© 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. 14071
    Prev
    Next
    INDEX
    Explanations

    geographical locations and political references, potentially related to military activities, conflicts, and political events

    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
    343
    +0.09
    0.6%
    223
    +0.09
    0.5%
    699
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    651
    +0.09
    0.10
    88
    +0.09
    0.08
    645
    +0.08
    0.07
    Negative Logits
    jriwal
    -0.64
    edIn
    -0.60
    maid
    -0.55
    --------------------------------------------------------
    -0.54
     Kush
    -0.53
    Reloaded
    -0.52
    âĹ¼
    -0.52
    holding
    -0.52
    irlf
    -0.51
    lled
    -0.50
    POSITIVE LOGITS
    ionics
    0.73
    ice
    0.70
    isco
    0.67
    itz
    0.65
    icer
    0.65
    uary
    0.64
    ices
    0.64
    atel
    0.63
    igr
    0.63
    iet
    0.63
    Activations Density 5.741%

    No Known Activations