© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 19396
    Prev
    Next
    INDEX
    Explanations

    statements about likelihood or probability

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating probability or likelihood of events or characteristics

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

    No Comments

    Negative Logits
    inth
    -0.91
    ornia
    -0.85
    inelli
    -0.78
    rief
    -0.78
    zeb
    -0.77
    andan
    -0.77
    illation
    -0.77
    shall
    -0.76
    inas
    -0.74
    uart
    -0.74
    POSITIVE LOGITS
     infer
    0.75
     likely
    0.75
     demographics
    0.73
     prey
    0.72
     responders
    0.70
     incarcer
    0.70
     Likely
    0.70
     encountering
    0.69
     underestimate
    0.68
     responses
    0.68
    Activations Density 0.020%

    No Known Activations