Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-RES-JB
    6. 20772
    Prev
    Next
    INDEX
    Explanations

    information about companies and production deals

    oai_token-act-pair · gpt-3.5-turbo

    references to publishing and media partnerships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ratom
    -0.77
    anon
    -0.70
     deport
    -0.68
    etooth
    -0.67
     intercepted
    -0.66
    é¾įå
    -0.65
    Äģ
    -0.65
     Aad
    -0.64
     overhe
    -0.64
     tooltip
    -0.64
    POSITIVE LOGITS
     distributor
    1.37
     Paramount
    1.37
     studios
    1.34
     Studios
    1.33
     Warner
    1.33
     Productions
    1.30
     Films
    1.29
     Entertainment
    1.28
     publisher
    1.24
     distributors
    1.20
    Activations Density 0.554%

    No Known Activations