© 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. 10-RES-JB
    11. 8092
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "narc" or related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to narcotics and despotic regimes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ting
    -0.79
     Hels
    -0.75
    forth
    -0.70
     Kaw
    -0.69
    ichen
    -0.69
    EVA
    -0.69
    tta
    -0.65
    lde
    -0.64
    FIELD
    -0.64
    held
    -0.64
    POSITIVE LOGITS
    otics
    1.61
    otic
    1.51
    inatory
    1.05
    osis
    0.97
    ology
    0.90
    ication
    0.88
    ogenic
    0.87
    inators
    0.86
    inating
    0.86
    rosis
    0.85
    Activations Density 0.057%

    No Known Activations