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. 8-RES-JB
    6. 5388
    Prev
    Next
    INDEX
    Explanations

    file extensions commonly used in computing

    oai_token-act-pair · gpt-3.5-turbo

    variations and references to external factors or influences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hari
    -0.81
    Reviewer
    -0.81
    Downloadha
    -0.77
    maid
    -0.74
    GES
    -0.71
     sharks
    -0.70
    UGH
    -0.70
    çĦ
    -0.68
    ker
    -0.68
    hare
    -0.67
    POSITIVE LOGITS
    racted
    1.73
    ensions
    1.57
    ension
    1.54
    ract
    1.50
    raction
    1.47
    inction
    1.45
    inct
    1.39
    ractor
    1.36
    ended
    1.36
    ortion
    1.34
    Activations Density 0.022%

    No Known Activations