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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 8047
    Prev
    Next
    INDEX
    Explanations

    phrases indicating hesitation or uncertainty

    oai_token-act-pair · gpt-3.5-turbo

    expressions of doubt or uncertainty

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

    No Comments

    Negative Logits
    agents
    -0.80
    inary
    -0.73
    rones
    -0.71
    asers
    -0.71
    YES
    -0.70
    Prince
    -0.70
    raltar
    -0.69
    jandro
    -0.69
    ptin
    -0.68
    voy
    -0.68
    POSITIVE LOGITS
     bothered
    1.06
     bother
    1.04
     anymore
    1.01
     bothering
    0.79
     anything
    0.76
     anywhere
    0.76
     bothers
    0.75
     liking
    0.73
     interested
    0.73
     remotely
    0.73
    Activations Density 0.033%

    No Known Activations