© 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. 3-RES-JB
    11. 15140
    Prev
    Next
    INDEX
    Explanations

    information about legal cases and police investigations

    oai_token-act-pair · gpt-3.5-turbo

    statements about awareness and knowledge regarding incidents or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ç¥ŀ
    -0.80
    !).
    -0.77
    ?).
    -0.69
    !".
    -0.68
     nerds
    -0.66
     ze
    -0.62
     splend
    -0.60
     squid
    -0.60
     ðŁĻĤ
    -0.60
     Starcraft
    -0.60
    POSITIVE LOGITS
     affidav
    0.97
     affidavit
    0.85
     briefed
    0.84
     contacted
    0.82
     redacted
    0.82
     confidential
    0.78
     notified
    0.78
     alerted
    0.77
     unidentified
    0.77
     subpoen
    0.76
    Activations Density 2.348%

    No Known Activations