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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 14308
    Prev
    Next
    INDEX
    Explanations

    instances of hesitance or unwillingness

    oai_token-act-pair · gpt-3.5-turbo

    expressions of hesitation or unwillingness

    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
    hemat
    -0.88
    tein
    -0.87
    alach
    -0.82
    mberg
    -0.80
    anza
    -0.80
    ramid
    -0.78
    abad
    -0.77
    scl
    -0.74
    urgy
    -0.74
    VERTISEMENT
    -0.71
    POSITIVE LOGITS
     reluctant
    0.92
     hesitant
    0.87
     shy
    0.80
     hesitation
    0.75
     reluctance
    0.75
     bargain
    0.72
     timid
    0.71
     undermin
    0.68
     trusting
    0.66
    WARE
    0.66
    Activations Density 0.022%

    No Known Activations