© 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. 11511
    Prev
    Next
    INDEX
    Explanations

    verbs indicating action, particularly those related to making decisions or conclusions

    oai_token-act-pair · gpt-3.5-turbo

    common auxiliary verbs and forms of the verb "to do."

    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
     welf
    -0.78
     destro
    -0.72
     warr
    -0.71
    peat
    -0.70
     rul
    -0.69
     advoc
    -0.67
     corrid
    -0.66
    ãĥ¼ãĥĨãĤ£
    -0.65
     nodd
    -0.65
     dilig
    -0.63
    POSITIVE LOGITS
    .
    0.94
    —
    0.81
    !
    0.81
    .[
    0.78
    ;
    0.78
    .<
    0.76
    ,
    0.76
    ãĢĤ
    0.75
    :
    0.75
     :)
    0.74
    Activations Density 0.576%

    No Known Activations