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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 8-RES-JB
    6. 20447
    Prev
    Next
    INDEX
    Explanations

    descriptions related to cooking times and ingredients in recipes

    oai_token-act-pair · gpt-3.5-turbo

    box office earnings of blockbuster films

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fixme
    -0.22
    rawdownloadcloneembedreportprint
    -0.17
     cheat
    -0.17
     mete
    -0.16
     Âł
    -0.16
     damned
    -0.16
    [/
    -0.16
     Donation
    -0.15
     dod
    -0.15
     dyn
    -0.15
    POSITIVE LOGITS
    ģ«
    0.22
    Ĭ±
    0.21
    ·
    0.19
    isma
    0.19
    romptu
    0.19
    ãĥŁ
    0.19
    iola
    0.18
    ©¶æ
    0.18
    azard
    0.18
    ĵ
    0.17
    Activations Density 7.408%

    No Known Activations