© 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. 2-RES-JB
    11. 23928
    Prev
    Next
    INDEX
    Explanations

    calls to action or requests for assistance

    oai_token-act-pair · gpt-3.5-turbo

    calls for assistance or support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é¾
    -0.77
    Pict
    -0.74
    ithe
    -0.71
    ebook
    -0.71
    gran
    -0.69
    aval
    -0.66
    eely
    -0.64
    War
    -0.64
    punk
    -0.63
    ols
    -0.63
    POSITIVE LOGITS
    fully
    0.92
     facilitate
    0.80
     Desk
    0.80
     broker
    0.80
     Assist
    0.77
    meet
    0.77
     aid
    0.76
     assisting
    0.75
     alleviate
    0.72
    ģĸ
    0.70
    Activations Density 0.050%

    No Known Activations