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. 0-RES-JB
    6. 9323
    Prev
    Next
    INDEX
    Explanations

    terms related to distribution and contribution

    oai_token-act-pair · gpt-3.5-turbo

    terms related to distribution and contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     è£ıè
    -0.73
     hor
    -0.67
     knot
    -0.65
     openings
    -0.64
     disturb
    -0.63
     Hor
    -0.63
     Xan
    -0.62
     uncomfortable
    -0.62
     scratch
    -0.62
     discomfort
    -0.62
    POSITIVE LOGITS
    ribution
    3.71
    ributed
    3.45
    ribut
    3.43
    ributes
    3.04
    ribute
    2.71
    inguished
    1.68
    rib
    1.25
    aliation
    1.25
    rition
    1.18
    ractor
    1.16
    Activations Density 0.018%

    No Known Activations