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. 17569
    Prev
    Next
    INDEX
    Explanations

    phrases related to providing help or support

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "assist" and its variations

    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
    place
    -0.80
    Pict
    -0.73
    bur
    -0.72
    nu
    -0.72
    peror
    -0.68
    ban
    -0.68
    meat
    -0.63
    prison
    -0.63
    club
    -0.63
    é¾
    -0.62
    POSITIVE LOGITS
     assisting
    0.91
     assist
    0.89
     aids
    0.84
     assists
    0.78
     assistance
    0.77
     aid
    0.74
    ments
    0.73
     Desk
    0.72
    assisted
    0.72
     assisted
    0.71
    Activations Density 0.032%

    No Known Activations