© 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. 9-RES-JB
    11. 24044
    Prev
    Next
    INDEX
    Explanations

    technical or scientific terms related to brain function and cognitive research

    oai_token-act-pair · gpt-3.5-turbo

    terms related to functional analysis and brain imaging

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    xual
    -0.76
     Preferred
    -0.72
     Called
    -0.72
    rir
    -0.66
    yang
    -0.65
    Wa
    -0.65
     passionately
    -0.65
    BOOK
    -0.64
     leveled
    -0.63
    Company
    -0.63
    POSITIVE LOGITS
    ities
    1.43
    istic
    1.36
    ization
    1.33
    ized
    1.33
    izations
    1.27
    isations
    1.23
    isation
    1.22
    izing
    1.21
    izable
    1.14
    istically
    1.14
    Activations Density 0.073%

    No Known Activations