© 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. 7-RES-JB
    11. 23402
    Prev
    Next
    INDEX
    Explanations

    security-related terms and issues

    oai_token-act-pair · gpt-3.5-turbo

    references to security-related issues and concerns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oric
    -0.92
    kson
    -0.78
    hes
    -0.73
    ICA
    -0.72
    sembly
    -0.72
    erers
    -0.68
    igible
    -0.66
    zl
    -0.66
    ascar
    -0.66
    lem
    -0.65
    POSITIVE LOGITS
    policy
    0.85
     breaches
    0.80
     vulnerabilities
    0.80
     clearance
    0.79
     guards
    0.79
     checkpoints
    0.78
     Breach
    0.78
     lapse
    0.78
     enforcement
    0.77
     advis
    0.76
    Activations Density 0.030%

    No Known Activations