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

    Neuronpedia

    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. 13602
    Prev
    Next
    INDEX
    Explanations

    information related to potential threats or risks

    oai_token-act-pair · gpt-3.5-turbo

    references to threats or risks, particularly in relation to posed challenges or dangers

    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
    ocket
    -0.67
    ergy
    -0.66
     conglomer
    -0.63
    itsch
    -0.62
    tery
    -0.61
    lex
    -0.60
    audi
    -0.60
     peg
    -0.59
    watch
    -0.58
    @#&
    -0.58
    POSITIVE LOGITS
    idon
    1.14
     posed
    0.82
    atoon
    0.82
    hran
    0.81
     pose
    0.76
     poses
    0.76
     Danger
    0.75
     hazards
    0.75
     dangers
    0.72
    nces
    0.71
    Activations Density 0.032%

    No Known Activations