Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 3354
    Prev
    Next
    INDEX
    Explanations

    instances of refusal or resistance

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "refuse" and its variations, indicating a focus on refusal or rejection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hetti
    -0.76
    ochond
    -0.75
    è¦ļéĨĴ
    -0.74
    ICAN
    -0.74
    ammy
    -0.73
    APH
    -0.71
    Assembly
    -0.71
    estern
    -0.70
    groups
    -0.70
    bred
    -0.68
    POSITIVE LOGITS
    geon
    0.84
     vehemently
    0.76
    quit
    0.74
     miser
    0.73
    afe
    0.73
     adm
    0.72
     refusal
    0.71
     admission
    0.70
     outright
    0.69
     refuse
    0.68
    Activations Density 0.021%

    No Known Activations