Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 8606
    Prev
    Next
    INDEX
    Explanations

    file sizes in kilobytes

    oai_token-act-pair · gpt-3.5-turbo

    mentions of data sizes or storage capacity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ially
    -0.81
    éĹĺ
    -0.81
    ebus
    -0.80
    Reviewer
    -0.79
    inez
    -0.79
    afort
    -0.78
    ources
    -0.75
    antly
    -0.75
    lict
    -0.75
     Palestin
    -0.74
    POSITIVE LOGITS
    KB
    1.02
    kb
    0.77
    SIZE
    0.73
    obi
    0.70
    FOR
    0.70
    hops
    0.69
    atsu
    0.68
     KB
    0.67
     Bang
    0.65
    LAB
    0.65
    Activations Density 0.008%

    No Known Activations