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. 21713
    Prev
    Next
    INDEX
    Explanations

    file sizes expressed in megabytes (MB)

    oai_token-act-pair · gpt-3.5-turbo
    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
    zona
    -0.72
     abdom
    -0.67
     Martial
    -0.66
    terday
    -0.64
    ean
    -0.63
    theless
    -0.63
     Shape
    -0.61
     spirits
    -0.61
     Venus
    -0.61
     Serbian
    -0.61
    POSITIVE LOGITS
    utable
    0.94
    TeX
    0.90
    TI
    0.85
    ilit
    0.85
    MB
    0.84
    ITS
    0.83
    TA
    0.81
    ilitation
    0.79
    oru
    0.79
    Ts
    0.78
    Activations Density 0.005%

    No Known Activations