© 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. 10-RES-JB
    11. 5767
    Prev
    Next
    INDEX
    Explanations

    negative consequences or harmful impacts

    oai_token-act-pair · gpt-3.5-turbo

    actions or events associated with harm or negative consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocene
    -0.83
    Abstract
    -0.81
    Hz
    -0.69
    onyms
    -0.67
     ancestor
    -0.63
     randomly
    -0.62
    bage
    -0.60
    vironments
    -0.59
    ée
    -0.59
    ãĤ©
    -0.59
    POSITIVE LOGITS
     morale
    1.41
     credibility
    1.03
     perceptions
    1.01
     confidence
    1.00
     relations
    0.99
     efforts
    0.95
     prospects
    0.95
     hopes
    0.91
     negotiations
    0.90
     momentum
    0.87
    Activations Density 0.312%

    No Known Activations