© 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. 11-RES-JB
    11. 3317
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals involved in political or legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ighty
    -0.59
     Sovereign
    -0.56
     Newtown
    -0.56
     Cannes
    -0.52
     UT
    -0.52
     Seek
    -0.52
    aukee
    -0.51
    Americ
    -0.51
     Uni
    -0.51
    duc
    -0.51
    POSITIVE LOGITS
     died
    0.81
     countered
    0.79
     reciproc
    0.78
     meanwhile
    0.77
     himself
    0.76
    's
    0.75
     responded
    0.74
     herself
    0.73
     succumbed
    0.72
     disagreed
    0.69
    Activations Density 0.305%

    No Known Activations