© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 1988
    Prev
    Next
    INDEX
    Explanations

    references to a successful or proven history in a specific field

    oai_token-act-pair · gpt-3.5-turbo

    references to "track records" or similar phrases indicating past performance or history

    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
    LY
    -0.65
     pand
    -0.64
    vernment
    -0.61
    ately
    -0.59
    umbn
    -0.56
     Marketable
    -0.56
     Haram
    -0.56
     Cheryl
    -0.56
     Brav
    -0.55
     Spice
    -0.55
    POSITIVE LOGITS
    suit
    1.37
    suits
    1.25
    pad
    1.21
    record
    1.19
    tracks
    0.98
    ball
    0.97
    track
    0.97
    balls
    0.96
    runner
    0.88
    marks
    0.88
    Activations Density 0.040%

    No Known Activations