© 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. 18001
    Prev
    Next
    INDEX
    Explanations

    keywords related to sexual assault and crime

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases related to sexual assault and harassment

    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
    çĦ
    -0.81
    Side
    -0.79
    selves
    -0.76
    Econom
    -0.74
    cit
    -0.73
     cannabin
    -0.72
    imum
    -0.72
    Pull
    -0.70
    stanbul
    -0.70
    peror
    -0.69
    POSITIVE LOGITS
     prevention
    1.13
     epidemic
    1.01
     hotline
    1.00
     perpetrated
    0.99
     stigma
    0.98
     victims
    0.93
     Prevention
    0.92
     Awareness
    0.91
     allegations
    0.89
     Rape
    0.88
    Activations Density 0.117%

    No Known Activations