© 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. 4-RES-JB
    11. 15207
    Prev
    Next
    INDEX
    Explanations

    transitions indicating a contrast or shift in focus

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "However."

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

    No Comments

    Negative Logits
     Goth
    -0.66
    board
    -0.63
    cup
    -0.62
    stein
    -0.61
    uto
    -0.59
     award
    -0.59
    letter
    -0.58
    rieg
    -0.57
     parade
    -0.57
     speech
    -0.56
    POSITIVE LOGITS
    chery
    0.78
    CLASSIFIED
    0.78
    tons
    0.74
    lers
    0.74
     interestingly
    0.73
    theless
    0.72
    chers
    0.72
     importantly
    0.71
    BIL
    0.69
    THER
    0.67
    Activations Density 0.035%

    No Known Activations