© 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. 33434
    Prev
    Next
    INDEX
    Explanations

    long, complex words and phrases related to geopolitical, medical, technical, and ideological discourses

    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
    615
    +0.11
    0.6%
    739
    +0.10
    0.5%
    455
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    549
    +0.11
    0.07
    288
    +0.10
    0.18
    109
    +0.08
    0.08
    Negative Logits
     thumbs
    -0.59
     jobs
    -0.57
    */(
    -0.56
     ATK
    -0.56
    dden
    -0.54
    culosis
    -0.53
     GEAR
    -0.53
    tle
    -0.53
    USD
    -0.52
    sonian
    -0.52
    POSITIVE LOGITS
    ivably
    1.07
    assing
    0.86
    abil
    0.81
    lement
    0.80
    rence
    0.75
    bes
    0.73
    fect
    0.71
    rehens
    0.70
    abilities
    0.70
    ceptor
    0.68
    Activations Density 6.557%

    No Known Activations