© 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. 9-RES-JB
    6. 7403
    Prev
    Next
    INDEX
    Explanations

    mentions of possibilities or suggestions of actions involving someone or something

    oai_token-act-pair · gpt-3.5-turbo

    modal verbs indicating possibility or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Palest
    -0.82
    ciating
    -0.68
    ament
    -0.68
    ches
    -0.64
     Kush
    -0.63
    shall
    -0.62
    cies
    -0.59
     Constant
    -0.58
     Blank
    -0.57
     Lifetime
    -0.57
    POSITIVE LOGITS
     be
    1.05
    onna
    0.97
     have
    0.97
     owe
    0.96
     someday
    0.95
     retaliate
    0.93
    bes
    0.88
     want
    0.87
     lose
    0.85
     suffer
    0.84
    Activations Density 0.137%

    No Known Activations