© 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. 2-RES-JB
    11. 9417
    Prev
    Next
    INDEX
    Explanations

    ways of physically interacting or coming into contact with things

    oai_token-act-pair · gpt-3.5-turbo

    references to the action of rubbing or similar tactile interactions

    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
     Hurricanes
    -0.69
    velength
    -0.67
    EMP
    -0.65
     embr
    -0.64
    akuya
    -0.63
    éĹĺ
    -0.61
    ruct
    -0.61
     Pilgrim
    -0.61
     Arc
    -0.60
    ortex
    -0.60
    POSITIVE LOGITS
     rub
    1.05
    bing
    1.00
    rics
    0.89
    bles
    0.86
    bers
    0.84
    bery
    0.82
    der
    0.78
     elbows
    0.76
    tp
    0.75
    bling
    0.74
    Activations Density 0.009%

    No Known Activations