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. 23540
    Prev
    Next
    INDEX
    Explanations

    various types of buildings and infrastructure

    oai_token-act-pair · gpt-3.5-turbo

    nouns related to various types of infrastructure and public services

    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
    JM
    -0.64
     Canaver
    -0.59
     Finch
    -0.58
    ãĤ¨ãĥ«
    -0.54
     Grassley
    -0.54
    è£ħ
    -0.53
    ULTS
    -0.50
    URR
    -0.49
    Ô
    -0.48
     VERS
    -0.48
    POSITIVE LOGITS
     etc
    1.10
    ).[
    0.73
    ).
    0.63
     thereof
    0.63
    )."
    0.62
     versa
    0.60
    )).
    0.59
     respectively
    0.59
    !).
    0.59
    );
    0.55
    Activations Density 1.483%

    No Known Activations