© 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. 33553
    Prev
    Next
    INDEX
    Explanations

    information pertaining to personal profiles or biographical details of individuals

    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
    0.9%
    701
    +0.12
    0.5%
    661
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.23
    0.34
    283
    +0.12
    0.01
    756
    +0.11
    -0.22
    Negative Logits
     Vaughan
    -0.77
     mend
    -0.76
     annexation
    -0.70
     Heller
    -0.70
     Hat
    -0.67
     conservatism
    -0.65
     Amend
    -0.65
     Situation
    -0.65
     Greenwood
    -0.64
    rah
    -0.63
    POSITIVE LOGITS
    EVA
    0.88
    tan
    0.86
    unders
    0.86
    powers
    0.85
    pton
    0.85
    iton
    0.81
    FW
    0.80
    ahime
    0.80
    AMI
    0.80
    ECA
    0.78
    Activations Density 21.990%

    No Known Activations