© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 23440
    Prev
    Next
    INDEX
    Explanations

    phrases related to uncertainty or confusion about ongoing events

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the phrase "what's going on."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Horus
    -0.74
    peria
    -0.72
    ullah
    -0.72
    ablo
    -0.67
     este
    -0.66
    ament
    -0.63
    heim
    -0.63
    ilitarian
    -0.62
    essor
    -0.62
    osal
    -0.62
    POSITIVE LOGITS
     downhill
    0.86
    Ń·
    0.82
    verning
    0.81
    lems
    0.75
    ±
    0.74
    ggle
    0.74
    ãĥ£
    0.73
    Īè
    0.72
     overboard
    0.72
    ij
    0.71
    Activations Density 0.053%

    No Known Activations