© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 16435
    Prev
    Next
    INDEX
    Explanations

    instances of the word "refusal."

    oai_token-act-pair · gpt-3.5-turbo
    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
    ets
    -0.70
     beaut
    -0.69
    paces
    -0.68
    rients
    -0.67
    »Ĵ
    -0.67
     safely
    -0.66
     tuned
    -0.64
     located
    -0.64
    pixel
    -0.64
    Featured
    -0.64
    POSITIVE LOGITS
     refusal
    3.29
     unwillingness
    2.38
     reluctance
    2.21
     insistence
    2.19
     inability
    2.14
     rejection
    1.97
     willingness
    1.93
     failure
    1.78
     denial
    1.76
     dismissal
    1.64
    Activations Density 0.033%

    No Known Activations