© 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. 3-RES-JB
    11. 22610
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences emphasizing one particular aspect or entity compared to others

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "not only" indicating a contrast or addition in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    insula
    -0.71
     largeDownload
    -0.68
     Mushroom
    -0.65
    regate
    -0.62
    iths
    -0.62
    fell
    -0.60
    oided
    -0.60
    future
    -0.60
    glomer
    -0.60
    MU
    -0.59
    POSITIVE LOGITS
     anymore
    0.85
    ifiable
    0.74
     passively
    0.74
     obe
    0.68
    til
    0.65
     remotely
    0.65
     incidentally
    0.64
     scratches
    0.64
     whatsoever
    0.63
     kidding
    0.62
    Activations Density 0.026%

    No Known Activations