© 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. 8-RES-JB
    11. 17246
    Prev
    Next
    INDEX
    Explanations

    phrases related to criticism or negative judgment

    oai_token-act-pair · gpt-3.5-turbo

    unique punctuation marks and their frequencies in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imum
    -0.88
     PTS
    -0.81
     Flavoring
    -0.78
     GEAR
    -0.77
    ERO
    -0.76
    inction
    -0.75
    ESA
    -0.75
    terday
    -0.75
    SHIP
    -0.74
    availability
    -0.74
    POSITIVE LOGITS
     charismatic
    1.01
     bearded
    1.00
     thirsty
    0.97
     rebellious
    0.95
     adventurous
    0.93
     hungry
    0.92
     sweaty
    0.92
    haired
    0.91
     aggressive
    0.91
     educated
    0.91
    Activations Density 0.154%

    No Known Activations