© 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. 9241
    Prev
    Next
    INDEX
    Explanations

    words related to libraries and librarians, and words related to vibrations and alerts

    oai_token-act-pair · gpt-3.5-turbo

    references to libraries and librarians

    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
    Ĥ¬
    -0.75
    chal
    -0.73
    WARD
    -0.68
     Derby
    -0.67
     mitigation
    -0.67
    corn
    -0.64
    houses
    -0.64
    mits
    -0.63
    fixed
    -0.63
    dds
    -0.61
    POSITIVE LOGITS
    ibr
    1.15
    arians
    1.04
    acies
    1.04
    inx
    1.01
    inet
    0.96
    ulus
    0.95
    andom
    0.94
    ators
    0.93
    ancies
    0.93
    ations
    0.90
    Activations Density 0.010%

    No Known Activations