© 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. 22459
    Prev
    Next
    INDEX
    Explanations

    conditional phrases suggesting different scenarios or possibilities

    oai_token-act-pair · gpt-3.5-turbo

    phrases that introduce examples or specifics

    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
     oun
    -0.85
    ò
    -0.82
     tiss
    -0.79
    ß
    -0.78
    Þ
    -0.77
    ©¶æ
    -0.76
    ccording
    -0.75
     destro
    -0.74
    aution
    -0.74
    oreAnd
    -0.72
    POSITIVE LOGITS
     as
    1.14
    as
    0.82
    As
    0.66
    paren
    0.61
    APD
    0.59
    thumbnails
    0.59
    iner
    0.59
    asher
    0.55
    amount
    0.53
    asant
    0.53
    Activations Density 0.043%

    No Known Activations