© 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. 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. 6081
    Prev
    Next
    INDEX
    Explanations

    information related to communications or messages, specifically involving hearing from or contacting others

    oai_token-act-pair · gpt-3.5-turbo

    points of decision or action

    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
     VS
    -0.57
    uilding
    -0.56
     dimensional
    -0.56
     pione
    -0.55
    Gaming
    -0.55
    senal
    -0.55
    ipation
    -0.52
     utilization
    -0.52
    hao
    -0.51
     Gaming
    -0.50
    POSITIVE LOGITS
     elsewhere
    0.74
     apiece
    0.61
     Abbas
    0.61
     GOODMAN
    0.61
     Belfast
    0.60
     unden
    0.59
     afterward
    0.59
    ,—
    0.59
     Mulcair
    0.55
    Otherwise
    0.54
    Activations Density 1.649%

    No Known Activations