© 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. 9-RES-JB
    11. 13256
    Prev
    Next
    INDEX
    Explanations

    references to sensitive or controversial topics and events in video content

    oai_token-act-pair · gpt-3.5-turbo

    content related to sensitive or offensive topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eworks
    -0.95
    beam
    -0.83
    Iterator
    -0.82
    */(
    -0.76
     conclud
    -0.75
    module
    -0.75
    anship
    -0.68
    alion
    -0.67
    Timer
    -0.67
     Defin
    -0.67
    POSITIVE LOGITS
     nudity
    0.98
     homosexuality
    0.96
     Adolf
    0.94
     celebrities
    0.94
     pedoph
    0.93
     deceased
    0.90
     genitals
    0.90
     Holocaust
    0.90
     menstru
    0.89
     nude
    0.89
    Activations Density 0.622%

    No Known Activations