© 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. 0-RES-JB
    11. 1107
    Prev
    Next
    INDEX
    Explanations

    the word "bird" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    words related to birds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     attendance
    -0.69
     Tem
    -0.68
     scales
    -0.68
     Elys
    -0.67
     corrosion
    -0.66
     attempts
    -0.65
     Cal
    -0.62
     OpenGL
    -0.62
     attrition
    -0.61
     Conquest
    -0.61
    POSITIVE LOGITS
    ird
    4.65
    irds
    1.99
    irst
    1.60
    IRD
    1.57
    ild
    1.25
    irt
    1.12
    bsite
    1.08
    irc
    1.06
    urd
    1.02
    foundland
    1.01
    Activations Density 0.011%

    No Known Activations