© 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. 24125
    Prev
    Next
    INDEX
    Explanations

    references to arrests and arrest warrants

    oai_token-act-pair · gpt-3.5-turbo

    references to arrests and legal actions

    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
    ÃŁ
    -0.71
    ^^^^
    -0.71
     snipp
    -0.66
    abbit
    -0.64
     dressing
    -0.62
    ¯¯¯¯
    -0.58
    ertility
    -0.57
     embr
    -0.57
     deceive
    -0.56
    burn
    -0.56
    POSITIVE LOGITS
     warrant
    1.31
     warrants
    1.28
    ees
    1.23
     Warrant
    1.20
     affidavit
    1.00
    ee
    0.98
    rained
    0.90
    able
    0.89
    ments
    0.88
     arrest
    0.87
    Activations Density 0.063%

    No Known Activations