© 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. 6417
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical locations or structures like "burrows"

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances or patterns of the word "rows."

    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
    piece
    -0.66
     circumstance
    -0.65
    ãĥ¼ãĥĨ
    -0.65
     Kenyan
    -0.63
     Scandinavian
    -0.63
     PLAN
    -0.62
     dearly
    -0.60
     incentive
    -0.59
     plate
    -0.59
     nomine
    -0.58
    POSITIVE LOGITS
    rows
    1.15
    restling
    1.07
    icz
    1.06
    hip
    0.98
    olver
    0.98
    ski
    0.95
    abies
    0.87
    ight
    0.85
    orld
    0.85
    ighting
    0.85
    Activations Density 0.006%

    No Known Activations