© 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. 1-RES-JB
    11. 24125
    Prev
    Next
    INDEX
    Explanations

    phrases or names with the letters "Bu" followed by a number, possibly representing a specific entity or concept

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Bu" followed by various contexts or subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Introduced
    -0.77
    wear
    -0.77
    heid
    -0.74
    dash
    -0.73
    likely
    -0.71
    */(
    -0.70
    working
    -0.68
    bucks
    -0.66
    graph
    -0.66
    dress
    -0.64
    POSITIVE LOGITS
     Bu
    1.24
    Bu
    0.98
    undai
    0.88
    arded
    0.86
    selage
    0.84
    xton
    0.82
    isons
    0.81
    igslist
    0.81
    arten
    0.77
    gment
    0.77
    Activations Density 0.004%

    No Known Activations