© 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. 4-RES-JB
    11. 6823
    Prev
    Next
    INDEX
    Explanations

    terms related to different types of abuse

    oai_token-act-pair · gpt-3.5-turbo

    instances and discussions of abuse

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

    No Comments

    Negative Logits
    travel
    -0.81
    cil
    -0.77
    izen
    -0.76
    pard
    -0.70
     traveler
    -0.70
     adventurer
    -0.68
     Gork
    -0.68
    views
    -0.67
    printed
    -0.67
    puter
    -0.66
    POSITIVE LOGITS
    abuse
    1.06
     abuse
    1.01
     abused
    0.99
     abusing
    0.94
     abuses
    0.90
     Abuse
    0.86
     inflicted
    0.84
     perpetrated
    0.78
     victims
    0.77
     abusers
    0.75
    Activations Density 0.019%

    No Known Activations