© 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. 8391
    Prev
    Next
    INDEX
    Explanations

    words related to libraries or librarians

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "library" and related variations

    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
    chal
    -0.79
    corn
    -0.76
    Ĥ¬
    -0.71
     quo
    -0.67
    fixed
    -0.66
    mits
    -0.66
     Derby
    -0.65
     mitigation
    -0.64
    fits
    -0.64
     Spice
    -0.63
    POSITIVE LOGITS
    ibr
    1.18
    ulus
    0.99
    acies
    0.96
    arians
    0.96
    ationally
    0.89
    ators
    0.89
    inx
    0.88
    ilib
    0.87
    ations
    0.87
    anting
    0.87
    Activations Density 0.005%

    No Known Activations