© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3-RES-JB
    6. 8933
    Prev
    Next
    INDEX
    Explanations

    words related to increasing or intensifying actions or situations

    oai_token-act-pair · gpt-3.5-turbo

    financial or numerical terms related to significant quantities or metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Grade
    -0.65
     Maher
    -0.62
    nw
    -0.57
     earliest
    -0.56
     Corps
    -0.55
    CLA
    -0.54
     backstage
    -0.54
     Lal
    -0.53
    WARN
    -0.53
     Survivor
    -0.53
    POSITIVE LOGITS
    ammy
    0.85
    rontal
    0.81
    ï¸ı
    0.80
    rencies
    0.76
    oche
    0.73
    hemy
    0.73
    fect
    0.72
    alion
    0.70
    Unix
    0.70
    agos
    0.70
    Activations Density 0.219%

    No Known Activations