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

    Neuronpedia

    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. 40844
    Prev
    Next
    INDEX
    Explanations

    discussions about legislative and policy interventions related to financial matters and societal wellbeing

    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
    +0.33
    1.5%
    481
    +0.16
    0.7%
    393
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    718
    +0.33
    0.22
    566
    +0.16
    0.17
    551
    +0.12
    0.16
    Negative Logits
    igma
    -0.68
    pires
    -0.63
    thing
    -0.61
    Tumblr
    -0.60
    ZI
    -0.59
     Slayer
    -0.59
    ament
    -0.59
    ance
    -0.58
    reality
    -0.58
    ustainable
    -0.57
    POSITIVE LOGITS
     be
    1.00
     arrive
    0.93
     become
    0.85
     derive
    0.85
     also
    0.85
     likewise
    0.85
     continue
    0.82
     propose
    0.81
     incorporate
    0.80
     begin
    0.80
    Activations Density 10.060%

    No Known Activations