© 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. 18701
    Prev
    Next
    INDEX
    Explanations

    instructions or advice related to personal care and household maintenance

    oai_token-act-pair · gpt-3.5-turbo

    instructions or recommendations for personal care and hygiene

    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
    arcity
    -0.84
    Independent
    -0.79
    soDeliveryDate
    -0.76
     Haram
    -0.75
    APD
    -0.68
    MP
    -0.67
    Rus
    -0.66
    ipolar
    -0.66
    Legend
    -0.65
    iphany
    -0.65
    POSITIVE LOGITS
     surfaces
    1.55
     skin
    1.42
     cheeks
    1.33
     clothes
    1.27
     palms
    1.22
     floors
    1.22
     surface
    1.18
     lips
    1.17
     clothing
    1.17
     garments
    1.16
    Activations Density 0.234%

    No Known Activations