© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 9265
    Prev
    Next
    INDEX
    Explanations

    specific mentions of notebooks

    oai_token-act-pair · gpt-3.5-turbo

    references to notebooks and diaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Interstitial
    -0.83
    maxwell
    -0.80
    ÑĢ
    -0.80
    reek
    -0.76
    н
    -0.71
    Ĵ
    -0.71
    aci
    -0.71
    oded
    -0.66
    aft
    -0.66
    uart
    -0.65
    POSITIVE LOGITS
     notebook
    1.30
     notebooks
    1.20
    BOOK
    0.82
    book
    0.82
    books
    0.81
     drawer
    0.76
     cartridges
    0.75
    tops
    0.73
     Pages
    0.73
    cases
    0.72
    Activations Density 0.005%

    No Known Activations