© 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. 7-RES-JB
    11. 8011
    Prev
    Next
    INDEX
    Explanations

    phrases related to sexual misconduct and inappropriate behavior

    oai_token-act-pair · gpt-3.5-turbo

    references to sexual misconduct and exploitation involving minors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pmwiki
    -0.92
     looting
    -0.91
     citations
    -0.83
    Ü
    -0.81
     EDITION
    -0.80
     antid
    -0.78
    govtrack
    -0.78
     mobilized
    -0.78
     audits
    -0.78
    £ı
    -0.77
    POSITIVE LOGITS
    girls
    1.25
     girls
    1.24
    girl
    1.24
    female
    1.21
     girl
    1.20
     females
    1.18
    male
    1.17
    girlfriend
    1.14
     breasts
    1.14
     female
    1.12
    Activations Density 1.131%

    No Known Activations