© 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. 11-RES-JB
    11. 20443
    Prev
    Next
    INDEX
    Explanations

    mentions of darkness or low lighting conditions

    oai_token-act-pair · gpt-3.5-turbo

    references to 'pitch' in various 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
    iliary
    -0.84
    liness
    -0.84
    hips
    -0.83
    uous
    -0.69
     Carbuncle
    -0.69
     Lauder
    -0.63
    ennial
    -0.63
    ial
    -0.62
    orate
    -0.62
     captcha
    -0.61
    POSITIVE LOGITS
    fork
    1.55
    caster
    0.86
    casters
    0.84
    for
    0.81
    idon
    0.78
    veyard
    0.76
    ITCH
    0.74
     pitch
    0.72
    perfect
    0.72
     pitched
    0.71
    Activations Density 0.046%

    No Known Activations