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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 20161
    Prev
    Next
    INDEX
    Explanations

    names related to various universities and individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or entities related to Birmingham and their roles or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     grid
    -0.68
     nomine
    -0.65
     Tune
    -0.63
     tune
    -0.60
     vain
    -0.60
    eur
    -0.58
     quake
    -0.57
     skilled
    -0.57
     distressed
    -0.56
     sear
    -0.56
    POSITIVE LOGITS
     Bir
    1.21
    Bir
    1.06
    git
    1.03
    mingham
    0.89
    keley
    0.87
    combe
    0.86
    neys
    0.86
    acle
    0.85
    glers
    0.85
    gement
    0.84
    Activations Density 0.008%

    No Known Activations