© 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. 9-RES-JB
    11. 5075
    Prev
    Next
    INDEX
    Explanations

    key actions or events happening in a narrative

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to conflict and tension

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     crap
    -0.68
     everybody
    -0.66
     Nobody
    -0.61
    !!!!!!!!
    -0.61
     blah
    -0.61
     Stuff
    -0.60
     shit
    -0.59
     stuff
    -0.59
     Everybody
    -0.59
     guy
    -0.58
    POSITIVE LOGITS
    vertisement
    0.73
    blance
    0.63
    enture
    0.63
    âĵĺ
    0.61
    anmar
    0.59
    uterte
    0.59
     istg
    0.56
    merce
    0.56
    oÄŁ
    0.55
    ï¸
    0.55
    Activations Density 1.950%

    No Known Activations