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. 1604
    Prev
    Next
    INDEX
    Explanations

    percentage values

    oai_token-act-pair · gpt-3.5-turbo

    percentage figures related to statistics or measurements

    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
     dign
    -0.74
    itiz
    -0.72
     Rav
    -0.72
     glim
    -0.70
     showc
    -0.69
     princ
    -0.68
    pload
    -0.68
    iden
    -0.65
     compan
    -0.64
     cru
    -0.64
    POSITIVE LOGITS
    +)
    0.95
    +.
    0.94
    %
    0.82
    +,
    0.82
    +
    0.80
    %.
    0.77
    bps
    0.76
    %-
    0.74
    fps
    0.72
    rowth
    0.72
    Activations Density 0.060%

    No Known Activations