© 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 EvalsExportsinterp-engineNEWAPI 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. 23426
    Prev
    Next
    INDEX
    Explanations

    keywords indicating attempts to communicate or get in touch with someone

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to joining and contacting individuals for comments or statements

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     occurrence
    -0.68
     convergence
    -0.62
     genesis
    -0.62
    ggles
    -0.59
     LIM
    -0.56
     compulsion
    -0.56
     aber
    -0.54
    Forest
    -0.54
     bladder
    -0.54
     itself
    -0.54
    POSITIVE LOGITS
     aback
    1.03
    icent
    0.88
     by
    0.88
    inet
    0.88
    igating
    0.86
    iere
    0.82
    ragon
    0.77
    oing
    0.75
    onna
    0.75
    hematically
    0.75
    Activations Density 0.355%

    No Known Activations