© 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. 4-RES-JB
    11. 10139
    Prev
    Next
    INDEX
    Explanations

    mentions of hacking-related activities, specifically instances of hacking and compromised systems

    oai_token-act-pair · gpt-3.5-turbo

    terms related to cyber attacks and hacking events

    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
    Wheel
    -0.73
    imental
    -0.68
    zl
    -0.68
    uces
    -0.67
    cil
    -0.65
    entary
    -0.65
    enment
    -0.64
    eca
    -0.62
    inances
    -0.62
     unification
    -0.62
    POSITIVE LOGITS
    ionage
    0.99
    CVE
    0.91
    threat
    0.85
     penetrated
    0.82
     trove
    0.81
     hacking
    0.81
     targeting
    0.81
     hacked
    0.79
     threat
    0.78
     fingerprints
    0.78
    Activations Density 0.060%

    No Known Activations