© 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 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. 33648
    Prev
    Next
    INDEX
    Explanations

    geographical locations and conflicts, particularly related to the Middle East and Africa

    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
    +0.19
    0.9%
    288
    +0.18
    0.9%
    326
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    496
    +0.19
    0.14
    288
    +0.18
    0.17
    326
    +0.11
    0.16
    Negative Logits
    ablishment
    -0.91
    ainer
    -0.75
     LAPD
    -0.74
    orsche
    -0.72
     Lovecraft
    -0.71
    ierrez
    -0.71
    âķIJâķIJ
    -0.70
    ciation
    -0.69
    antly
    -0.67
     Dame
    -0.66
    POSITIVE LOGITS
    ites
    0.91
    beans
    0.83
    ite
    0.79
    itic
    0.76
    ua
    0.73
    bean
    0.73
    atar
    0.72
    halla
    0.70
    awi
    0.68
    inia
    0.67
    Activations Density 5.163%

    No Known Activations