Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 12978
    Prev
    Next
    INDEX
    Explanations

    the name "Crow" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals named Crow, indicating focus on a specific character or person in the text

    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
    ugal
    -0.78
    utation
    -0.71
    uated
    -0.70
    itute
    -0.70
    inen
    -0.70
    itude
    -0.68
    itia
    -0.67
    aternity
    -0.67
    icient
    -0.66
    iciency
    -0.65
    POSITIVE LOGITS
    bars
    1.13
    crow
    1.05
     Crow
    1.03
    bones
    0.99
    hawk
    0.90
     Heights
    0.90
    bar
    0.89
    vine
    0.87
    der
    0.87
    shaw
    0.84
    Activations Density 0.023%

    No Known Activations