© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10-RES-JB
    11. 1286
    Prev
    Next
    INDEX
    Explanations

    expressions of uncertainty or contemplation, often involving contrasting possibilities

    oai_token-act-pair · gpt-3.5-turbo

    interrogative phrases or rhetorical questions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /
    -0.77
    efer
    -0.68
    then
    -0.68
    \":
    -0.68
    onds
    -0.68
    ISON
    -0.67
    EMS
    -0.67
    enegger
    -0.66
    ãĥ£
    -0.65
    ords
    -0.65
    POSITIVE LOGITS
     simply
    1.26
     merely
    1.15
     just
    1.01
     outright
    1.01
     downright
    0.99
     alternatively
    0.94
     unlucky
    0.92
     indifferent
    0.82
     sheer
    0.81
     else
    0.79
    Activations Density 0.203%

    No Known Activations