© 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. 6-RES-JB
    11. 2650
    Prev
    Next
    INDEX
    Explanations

    phrases related to sudden events or actions happening in a story

    oai_token-act-pair · gpt-3.5-turbo

    elements of a narrative involving unexpected events and characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ilty
    -0.73
    ateral
    -0.70
    iven
    -0.70
     reliant
    -0.68
     depend
    -0.68
    ahime
    -0.67
     understatement
    -0.67
    EStreamFrame
    -0.65
    ;;;;;;;;;;;;
    -0.63
    opia
    -0.63
    POSITIVE LOGITS
     suddenly
    0.86
    Suddenly
    0.76
     startled
    0.75
     bombshell
    0.73
     mysteriously
    0.72
     alerted
    0.72
     stranger
    0.71
     Suddenly
    0.70
     unexpectedly
    0.70
     mailed
    0.69
    Activations Density 0.720%

    No Known Activations