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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 8-RES-JB
    11. 12580
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or contemplation

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating uncertainty or speculation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itor
    -0.73
    âĹ¼
    -0.69
    çĶ°
    -0.68
    âĶĢâĶĢâĶĢâĶĢ
    -0.66
    erver
    -0.66
    ById
    -0.66
    tail
    -0.65
    cens
    -0.65
    par
    -0.64
    resistant
    -0.63
    POSITIVE LOGITS
     suffice
    1.45
     anecd
    1.22
     nevertheless
    1.00
     nonetheless
    0.98
     indications
    0.95
     guesses
    0.83
     anecdotal
    0.82
     broadly
    0.80
     gist
    0.75
     hopefully
    0.74
    Activations Density 0.176%

    No Known Activations