© 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. 8-RES-JB
    11. 22375
    Prev
    Next
    INDEX
    Explanations

    words related to corruption or unfair practices

    oai_token-act-pair · gpt-3.5-turbo

    references to corruption in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abwe
    -0.71
     Flavoring
    -0.70
    cule
    -0.66
    zig
    -0.66
     Anxiety
    -0.65
    ciation
    -0.65
    gap
    -0.65
    Downloadha
    -0.64
    yip
    -0.63
    ches
    -0.63
    POSITIVE LOGITS
    ly
    1.15
    ible
    1.02
    ions
    1.00
    nesses
    0.94
    NESS
    0.94
    ness
    0.91
    ibly
    0.88
    ingly
    0.85
    glers
    0.83
    iated
    0.80
    Activations Density 0.040%

    No Known Activations