© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 7780
    Prev
    Next
    INDEX
    Explanations

    mathematical or alphanumeric patterns within words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the letter 'b' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Laur
    -0.58
    lde
    -0.58
     Sark
    -0.58
    ÄŁ
    -0.57
    jad
    -0.57
     Kear
    -0.56
     Dayton
    -0.54
    eln
    -0.54
     Kik
    -0.53
    LM
    -0.53
    POSITIVE LOGITS
    inals
    0.88
    oreal
    0.82
    itect
    0.79
    itory
    0.77
    orescent
    0.77
    abetic
    0.76
    atures
    0.73
    itude
    0.72
    itives
    0.69
    ivable
    0.69
    Activations Density 0.077%

    No Known Activations