© 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. 3-RES-JB
    6. 15069
    Prev
    Next
    INDEX
    Explanations

    verbs or phrases related to refusal or resistance

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "refuse" and its variants regarding denial or rejection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¦ļéĨĴ
    -0.83
    groups
    -0.75
    hetti
    -0.73
    otor
    -0.73
    ammy
    -0.73
    estern
    -0.71
    arya
    -0.70
    otive
    -0.69
    agame
    -0.68
    amate
    -0.68
    POSITIVE LOGITS
     miser
    0.84
     refuse
    0.80
    bryce
    0.76
     refusal
    0.74
     vehemently
    0.73
    quit
    0.73
     refuses
    0.72
     admission
    0.69
    geon
    0.68
    ĸļ
    0.68
    Activations Density 0.022%

    No Known Activations