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. 5-RES-JB
    6. 7726
    Prev
    Next
    INDEX
    Explanations

    references to the word "Bird"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Bird" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ilitary
    -0.81
    FINE
    -0.76
    bered
    -0.72
    untled
    -0.71
    oldemort
    -0.70
     unregulated
    -0.70
    acists
    -0.67
    rano
    -0.67
    idency
    -0.66
     cumbers
    -0.65
    POSITIVE LOGITS
    bird
    1.19
    bats
    1.09
    birds
    1.02
    zilla
    1.01
    seed
    0.99
    Bird
    0.98
     Bird
    0.98
    hawk
    0.96
    bath
    0.93
    walk
    0.93
    Activations Density 0.010%

    No Known Activations