© 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. 13536
    Prev
    Next
    INDEX
    Explanations

    unexpected developments or surprises in a narrative sequence

    oai_token-act-pair · gpt-3.5-turbo

    references to unexpected developments or plot twists

    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
    ufact
    -0.75
    leased
    -0.70
    hammad
    -0.69
    asking
    -0.68
    rahim
    -0.67
    estine
    -0.65
     Defenders
    -0.63
     appropriation
    -0.62
     Ducks
    -0.62
    league
    -0.62
    POSITIVE LOGITS
     twist
    1.15
     twists
    1.10
     Twist
    0.89
     endings
    0.80
     Whedon
    0.77
     twisting
    0.75
     weave
    0.74
     helic
    0.73
    abouts
    0.73
     angle
    0.70
    Activations Density 0.032%

    No Known Activations