© 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. 11-RES-JB
    11. 9148
    Prev
    Next
    INDEX
    Explanations

    news headlines related to violent incidents

    oai_token-act-pair · gpt-3.5-turbo

    terms related to violence, legal issues, and public safety incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }"
    -0.78
    then
    -0.73
    ]).
    -0.68
     tended
    -0.66
    Otherwise
    -0.65
    ynt
    -0.63
    ItemThumbnailImage
    -0.61
    âĶĢâĶĢâĶĢâĶĢ
    -0.60
    })
    -0.59
     THEN
    -0.58
    POSITIVE LOGITS
     following
    1.22
     after
    1.22
     amid
    1.18
     due
    1.03
    after
    1.01
    due
    0.93
     owing
    0.89
     Following
    0.83
     thanks
    0.83
     fearing
    0.81
    Activations Density 0.800%

    No Known Activations