© 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. 9-RES-JB
    11. 1317
    Prev
    Next
    INDEX
    Explanations

    related to the concept of rejection or refusal

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the act of rejecting or refusal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    brance
    -0.77
    ussen
    -0.75
    vern
    -0.73
    inki
    -0.69
    llular
    -0.69
    andise
    -0.69
    ixtape
    -0.68
    breaker
    -0.68
    isd
    -0.67
    dro
    -0.65
    POSITIVE LOGITS
     outright
    0.84
     hypotheses
    0.79
     suggestions
    0.78
    hap
    0.77
     excuses
    0.76
    REF
    0.74
     pleas
    0.74
     attempts
    0.72
     responsibility
    0.69
     propositions
    0.69
    Activations Density 0.052%

    No Known Activations