© 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 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. 0-RES-JB
    11. 12739
    Prev
    Next
    INDEX
    Explanations

    words signaling additional information or points of interest

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Also"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     determined
    -0.66
     desperate
    -0.62
     routine
    -0.60
     moments
    -0.60
     escape
    -0.59
     goodbye
    -0.59
     quarter
    -0.58
     dream
    -0.58
     century
    -0.58
     milliseconds
    -0.58
    POSITIVE LOGITS
    Also
    3.30
     Also
    2.19
    Additionally
    1.97
     ALSO
    1.94
    also
    1.78
    Lastly
    1.76
    Furthermore
    1.69
    Otherwise
    1.66
    Besides
    1.65
    Secondly
    1.62
    Activations Density 0.014%

    No Known Activations