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. 7332
    Prev
    Next
    INDEX
    Explanations

    names or references related to locations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Brook."

    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
    olkien
    -0.75
    arily
    -0.73
    UME
    -0.70
     conspicuous
    -0.69
    wcsstore
    -0.68
     lockout
    -0.67
     inflated
    -0.66
     prefrontal
    -0.66
     defective
    -0.66
    á¹
    -0.65
    POSITIVE LOGITS
    haven
    1.40
    er
    1.14
    brook
    1.10
    lyn
    1.09
    dale
    1.01
    Brook
    1.01
     Brook
    0.97
    side
    0.93
    lands
    0.93
    combe
    0.93
    Activations Density 0.012%

    No Known Activations