© 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. 33705
    Prev
    Next
    INDEX
    Explanations

    names of individuals along with medical terms and conditions

    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
    727
    +0.14
    0.6%
    211
    +0.14
    0.6%
    151
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.27
    326
    +0.14
    0.23
    151
    +0.13
    0.19
    Negative Logits
    otle
    -1.03
     Bastard
    -0.84
    ublic
    -0.84
    areth
    -0.80
    ept
    -0.79
     Played
    -0.78
    opher
    -0.77
    é¾įå
    -0.77
    ynthesis
    -0.74
    sonian
    -0.74
    POSITIVE LOGITS
    geon
    1.31
    geons
    1.27
    iosity
    1.22
    rier
    1.14
    rences
    1.10
    lock
    0.99
    iously
    0.98
     Rahman
    0.98
    witz
    0.97
    kish
    0.97
    Activations Density 7.842%

    No Known Activations