© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 31556
    Prev
    Next
    INDEX
    Explanations

    locations mentioned or related to Burma

    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
    +0.14
    0.6%
    95
    +0.11
    0.5%
    152
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.14
    0.32
    6
    +0.11
    0.18
    294
    +0.10
    0.03
    Negative Logits
    kefeller
    -0.78
    isSpecialOrderable
    -0.76
    merga
    -0.73
    icial
    -0.72
    bably
    -0.71
    incial
    -0.70
    icient
    -0.69
    parency
    -0.67
    ensitivity
    -0.66
     flares
    -0.64
    POSITIVE LOGITS
     Bunker
    0.77
     è£ıè
    0.74
     Cemetery
    0.70
    abase
    0.70
     Syndrome
    0.70
     Ashes
    0.67
    rants
    0.66
     Sleeping
    0.66
    aston
    0.66
     Corpse
    0.66
    Activations Density 18.104%

    No Known Activations