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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 1645
    Prev
    Next
    INDEX
    Explanations

    URLs starting with "https" in documents

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the "https" protocol in URLs

    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
     destro
    -0.83
     trave
    -0.82
    Ͻ
    -0.77
     neighb
    -0.71
    bos
    -0.70
     Morse
    -0.69
     Sierra
    -0.68
     territ
    -0.68
     contrace
    -0.67
     reluct
    -0.66
    POSITIVE LOGITS
    ://
    1.60
    :/
    1.00
    doi
    0.98
    archive
    0.91
    twitter
    0.83
    natureconservancy
    0.80
    docs
    0.79
    acial
    0.78
    archives
    0.74
    xt
    0.71
    Activations Density 0.009%

    No Known Activations