© 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. 4-RES-JB
    11. 1089
    Prev
    Next
    INDEX
    Explanations

    mentions of background checks, particularly related to legal and safety procedures

    oai_token-act-pair · gpt-3.5-turbo

    terms related to background checks and vetting processes

    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
    Ant
    -0.72
    jac
    -0.72
    Corn
    -0.69
    Anth
    -0.69
    quit
    -0.69
    minecraft
    -0.67
    hold
    -0.67
    Jay
    -0.67
    Pad
    -0.67
     pent
    -0.67
    POSITIVE LOGITS
     vetting
    0.94
    essee
    0.88
     vetted
    0.88
     dossier
    0.86
     procedures
    0.83
     troopers
    0.81
     checks
    0.81
     applicants
    0.78
    haar
    0.78
     examinations
    0.78
    Activations Density 0.026%

    No Known Activations