© 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. 10-RES-JB
    11. 11058
    Prev
    Next
    INDEX
    Explanations

    words related to legal or criminal actions and consequences

    oai_token-act-pair · gpt-3.5-turbo

    words related to violations, authority, and consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    apest
    -0.62
     realise
    -0.60
     avail
    -0.56
     endeavour
    -0.56
     decentral
    -0.56
     yours
    -0.54
     yeah
    -0.53
    Ô
    -0.53
     defin
    -0.52
    )=
    -0.52
    POSITIVE LOGITS
     during
    1.19
     amid
    1.05
     improperly
    0.98
    during
    0.97
     prematurely
    0.94
     inappropriately
    0.92
     onstage
    0.89
     while
    0.87
     midway
    0.80
     after
    0.78
    Activations Density 0.544%

    No Known Activations