© 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. 1659
    Prev
    Next
    INDEX
    Explanations

    phrases related to injuries or physical harm

    oai_token-act-pair · gpt-3.5-turbo

    mentions of events or gatherings

    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
    Therefore
    -0.72
     âī
    -0.71
    information
    -0.70
     nonviolent
    -0.70
     Therefore
    -0.68
     violates
    -0.64
     approximately
    -0.63
     defense
    -0.63
    ).[
    -0.63
    Furthermore
    -0.63
    POSITIVE LOGITS
     favourites
    0.96
     reckon
    0.85
     mould
    0.84
     snag
    0.83
     Yorkshire
    0.82
     NRL
    0.82
     flavours
    0.79
     Queensland
    0.79
     swoop
    0.77
    iverpool
    0.77
    Activations Density 1.355%

    No Known Activations