© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 11349
    Prev
    Next
    INDEX
    Explanations

    words related to refusal or denial

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "declined"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Offline
    -0.92
    neys
    -0.82
    è¦ļéĨĴ
    -0.81
    Clean
    -0.72
    Pur
    -0.71
    oned
    -0.71
    rod
    -0.70
    dam
    -0.69
    flo
    -0.69
    ãĤ·ãĥ£
    -0.69
    POSITIVE LOGITS
     declined
    1.12
     declines
    1.07
     declining
    0.77
     warr
    0.74
     escal
    0.74
     confir
    0.71
    ccoli
    0.71
     decline
    0.71
    yss
    0.70
     Krug
    0.69
    Activations Density 0.010%

    No Known Activations