© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6-RES-JB
    11. 8457
    Prev
    Next
    INDEX
    Explanations

    mentions of terrorist activities or threats

    oai_token-act-pair · gpt-3.5-turbo

    references to hijacking events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rite
    -0.89
    bleacher
    -0.71
     Thick
    -0.67
     Solitaire
    -0.67
     Veter
    -0.66
    20439
    -0.66
     Angels
    -0.64
    ç¥ŀ
    -0.64
    rose
    -0.63
     Bears
    -0.63
    POSITIVE LOGITS
     hij
    1.18
     hijacked
    0.99
    ackers
    0.83
    intosh
    0.82
    aline
    0.80
    ulence
    0.78
    acking
    0.74
    inx
    0.73
    eering
    0.72
    anism
    0.70
    Activations Density 0.019%

    No Known Activations