© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 14490
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to finance and economics

    oai_token-act-pair · gpt-3.5-turbo

    references to political contexts and sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    utz
    -0.69
    ITNESS
    -0.65
    uana
    -0.60
    âķIJâķIJ
    -0.59
    "},
    -0.53
     Fitz
    -0.53
    ADRA
    -0.53
     Liberation
    -0.51
    ertodd
    -0.51
    lisher
    -0.51
    POSITIVE LOGITS
    gently
    0.75
    rily
    0.74
     throats
    0.72
     onto
    0.72
    til
    0.72
    edly
    0.71
    ilaterally
    0.66
    hem
    0.65
     footsteps
    0.64
     havoc
    0.61
    Activations Density 1.119%

    No Known Activations