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. 9-RES-JB
    6. 22315
    Prev
    Next
    INDEX
    Explanations

    keywords related to different sports and technology publications

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to various sports and technology sectors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     secondary
    -0.67
     redeem
    -0.66
     hands
    -0.66
     scheme
    -0.65
     wheelchair
    -0.64
     convincing
    -0.64
     canoe
    -0.64
     autistic
    -0.63
     playable
    -0.63
     weakest
    -0.63
    POSITIVE LOGITS
     Digest
    1.17
    Blog
    1.12
     Insider
    1.12
    News
    1.09
    Ins
    1.09
     Matters
    1.08
    Week
    1.04
    pedia
    1.03
    Fix
    1.01
    Express
    1.01
    Activations Density 0.341%

    No Known Activations