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. 5712
    Prev
    Next
    INDEX
    Explanations

    phrases related to a daily dispatch newsletter

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Dispatch" and related terms

    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
    egal
    -0.78
    umber
    -0.78
    urt
    -0.73
    rd
    -0.73
    gio
    -0.69
    --+
    -0.68
    unal
    -0.67
    ipedia
    -0.66
    arson
    -0.64
    atever
    -0.64
    POSITIVE LOGITS
     Dispatch
    1.06
    Dispatch
    0.99
     dispatch
    0.88
    ables
    0.86
    DragonMagazine
    0.79
    Queue
    0.78
    hower
    0.75
    ivery
    0.73
    ãĥ¼ãĥĨãĤ£
    0.73
    able
    0.73
    Activations Density 0.018%

    No Known Activations