© 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. 18606
    Prev
    Next
    INDEX
    Explanations

    comparisons or contrasts between different things

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and phrases indicating contrast or comparison

    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
    ãĤ©
    -0.68
    isin
    -0.67
     guiActiveUn
    -0.64
    ikawa
    -0.63
    hei
    -0.63
    endor
    -0.62
    issance
    -0.61
    abama
    -0.60
    igen
    -0.60
    "]=>
    -0.59
    POSITIVE LOGITS
     others
    2.23
     Others
    2.14
    Others
    2.11
    some
    1.31
     some
    1.27
    Some
    1.08
     Some
    1.07
     SOME
    0.97
    other
    0.87
     other
    0.84
    Activations Density 0.262%

    No Known Activations