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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 14543
    Prev
    Next
    INDEX
    Explanations

    names containing the word "Crow"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Crow" in various contexts

    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
    ugal
    -0.74
    icient
    -0.70
     fateful
    -0.68
    ãĤ·ãĥ£
    -0.68
    ItemTracker
    -0.67
     candid
    -0.66
    aternity
    -0.66
     unexpected
    -0.65
     accidental
    -0.65
     Lisbon
    -0.65
    POSITIVE LOGITS
    crow
    1.19
    bars
    1.13
     Crow
    1.13
    bones
    1.05
    der
    1.03
    hawk
    1.01
    bats
    0.94
     Heights
    0.92
    bar
    0.91
    blade
    0.90
    Activations Density 0.013%

    No Known Activations