© 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. 10-RES-JB
    11. 20411
    Prev
    Next
    INDEX
    Explanations

    phrases indicating repetition or continuity

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize repetition or returning to a previous point

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eways
    -0.70
    adena
    -0.69
    ocene
    -0.68
    ottage
    -0.67
    izons
    -0.67
    oslav
    -0.64
    76561
    -0.64
    oming
    -0.63
    oreal
    -0.61
    л
    -0.59
    POSITIVE LOGITS
    nces
    0.76
     reiterate
    0.73
     illustrating
    0.72
     proving
    0.71
     echoing
    0.68
     quoting
    0.67
     revolving
    0.66
    tical
    0.65
     emphas
    0.65
     demonstrating
    0.65
    Activations Density 0.042%

    No Known Activations