© 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. 6131
    Prev
    Next
    INDEX
    Explanations

    phrases related to negotiations, deals, and plans

    oai_token-act-pair · gpt-3.5-turbo

    references to significant events or actions

    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
     differed
    -0.81
     tended
    -0.79
    ĸļ
    -0.75
     varied
    -0.75
     uncommon
    -0.74
    aned
    -0.72
     inconsist
    -0.71
     respondent
    -0.69
    requently
    -0.69
     discarded
    -0.69
    POSITIVE LOGITS
     tomorrow
    1.29
     gonna
    1.09
    Tomorrow
    1.05
     hopefully
    1.01
     ASAP
    1.00
     Tomorrow
    0.97
    Hopefully
    0.97
    maybe
    0.97
     tonight
    0.94
     Hopefully
    0.94
    Activations Density 1.117%

    No Known Activations