© 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. 18839
    Prev
    Next
    INDEX
    Explanations

    words related to being harmed or criticized

    oai_token-act-pair · gpt-3.5-turbo

    words related to harm or injury

    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
    enhagen
    -0.81
    UX
    -0.63
    aceae
    -0.63
    DragonMagazine
    -0.63
     Dragonbound
    -0.62
    leck
    -0.61
     Highlands
    -0.61
     Integrity
    -0.61
    sylv
    -0.61
    ynski
    -0.57
    POSITIVE LOGITS
    ried
    1.11
    ped
    1.10
    ping
    1.07
    red
    1.00
    bled
    0.99
    med
    0.97
    ved
    0.96
    ked
    0.95
    ivated
    0.94
    gered
    0.92
    Activations Density 0.146%

    No Known Activations