© 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. 4-RES-JB
    11. 7317
    Prev
    Next
    INDEX
    Explanations

    Common Vulnerabilities and Exposures (CVE) identifiers in technical information

    oai_token-act-pair · gpt-3.5-turbo

    references to Common Vulnerabilities and Exposures (CVE) and related security concepts

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

    No Comments

    Negative Logits
    crop
    -0.77
    chool
    -0.74
    imo
    -0.72
    yss
    -0.71
    amon
    -0.68
    zhen
    -0.66
    hov
    -0.65
    boro
    -0.65
    furt
    -0.64
    temp
    -0.64
    POSITIVE LOGITS
    enhagen
    0.89
    urers
    0.76
    manac
    0.75
     acknowled
    0.73
     IDs
    0.73
    erate
    0.71
     severity
    0.70
     Disclosure
    0.69
    overed
    0.69
    Sym
    0.68
    Activations Density 0.018%

    No Known Activations