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. 22144
    Prev
    Next
    INDEX
    Explanations

    words related to requesting, asking for, or seeking assistance or information

    oai_token-act-pair · gpt-3.5-turbo

    terms related to requests for donations or contributions

    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
     Aqu
    -0.77
    bur
    -0.69
    wreck
    -0.68
     Yard
    -0.67
    fall
    -0.65
    mk
    -0.64
     Underground
    -0.63
    board
    -0.63
    breaks
    -0.63
    este
    -0.62
    POSITIVE LOGITS
     solicit
    1.28
     solicitation
    1.18
     solic
    1.15
     bids
    0.90
    olicited
    0.85
    itta
    0.84
    ORS
    0.77
    yip
    0.74
     invitations
    0.74
     bribes
    0.73
    Activations Density 0.030%

    No Known Activations