© 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. 7-RES-JB
    11. 4383
    Prev
    Next
    INDEX
    Explanations

    references to the speaker or writer

    oai_token-act-pair · gpt-3.5-turbo

    references to personal experiences and identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Beir
    -0.78
     Equality
    -0.74
     HRC
    -0.70
     Finish
    -0.70
     recess
    -0.63
     Parenthood
    -0.63
     Mb
    -0.62
     Doors
    -0.59
     vacancy
    -0.59
     Rape
    -0.58
    POSITIVE LOGITS
    imei
    1.05
    adow
    1.04
    andering
    1.01
    adows
    0.97
    aning
    0.95
    hers
    0.94
    atics
    0.94
    atic
    0.94
    ubi
    0.89
    anders
    0.88
    Activations Density 0.114%

    No Known Activations