© 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. 7-RES-JB
    11. 17131
    Prev
    Next
    INDEX
    Explanations

    adverbs denoting degree or intensity

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the word "fairly" indicating a moderate level of certainty or intensity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jen
    -0.76
    ocene
    -0.73
     Delivery
    -0.72
    STER
    -0.70
    IAN
    -0.69
    uality
    -0.69
    HAEL
    -0.69
    RY
    -0.69
    iments
    -0.67
    igator
    -0.67
    POSITIVE LOGITS
     sized
    0.91
     priced
    0.86
     accurate
    0.86
     speaking
    0.85
     tame
    0.84
     compensated
    0.84
     straightforward
    0.81
     innocuous
    0.81
     harmless
    0.79
     benign
    0.78
    Activations Density 0.015%

    No Known Activations