© 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 EvalsExportsinterp-engineNEWAPI 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. 0-RES-JB
    11. 15180
    Prev
    Next
    INDEX
    Explanations

    verbs related to causing harm or impact on others

    oai_token-act-pair · gpt-3.5-turbo

    terms related to infection and alignment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gered
    -0.85
    written
    -0.80
    mentioned
    -0.80
    ledged
    -0.79
    answered
    -0.78
    itted
    -0.75
    umbled
    -0.75
    played
    -0.74
    olated
    -0.74
    arted
    -0.73
    POSITIVE LOGITS
     infect
    1.77
     instruct
    1.72
     enroll
    1.66
     encrypt
    1.62
     resurrect
    1.53
     incarcer
    1.52
     align
    1.49
     confess
    1.49
     demol
    1.49
     deflect
    1.46
    Activations Density 0.112%

    No Known Activations