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. 4-RES-JB
    6. 9887
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of "record" or "recording."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Rec" or related phrases, likely indicating a focus on recreational or related programs and their activities

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

    No Comments

    Negative Logits
    furt
    -0.85
    tips
    -0.72
    MENTS
    -0.69
     Kenyan
    -0.68
    ahime
    -0.66
    )=(
    -0.64
    loo
    -0.64
     Masters
    -0.64
    OPLE
    -0.62
     dash
    -0.62
    POSITIVE LOGITS
    ycle
    1.20
    ruit
    1.12
    urrent
    1.10
    ruits
    1.09
    ipient
    1.06
    oded
    1.02
    onnaissance
    0.98
    secut
    0.93
    oding
    0.92
    ipes
    0.91
    Activations Density 0.009%

    No Known Activations