© 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. 466
    Prev
    Next
    INDEX
    Explanations

    derogatory terms or insults

    oai_token-act-pair · gpt-3.5-turbo

    derogatory labels or insults directed at individuals

    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
     deliberations
    -0.77
     transitions
    -0.75
    anticipated
    -0.70
     Flavoring
    -0.70
    knit
    -0.70
     unfolding
    -0.70
    irtual
    -0.68
    ortality
    -0.68
    ersive
    -0.68
     Extended
    -0.66
    POSITIVE LOGITS
     liar
    1.56
     traitor
    1.38
     hypocr
    1.33
     bigot
    1.32
     whore
    1.28
     rapist
    1.23
     coward
    1.19
     racists
    1.19
     racist
    1.18
    fascist
    1.17
    Activations Density 0.393%

    No Known Activations