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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 4369
    Prev
    Next
    INDEX
    Explanations

    statements that lead to a conclusion or result

    oai_token-act-pair · gpt-3.5-turbo

    significant punctuation marks that indicate the end of statements

    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
     aven
    -0.79
    entin
    -0.69
     gou
    -0.66
     reven
    -0.65
     downed
    -0.65
    »Ĵ
    -0.64
     cumulative
    -0.63
     clos
    -0.63
     chron
    -0.62
    akra
    -0.61
    POSITIVE LOGITS
    However
    1.64
     However
    1.64
    But
    1.52
     But
    1.50
    BUT
    1.48
    but
    1.45
     Unfortunately
    1.37
     BUT
    1.33
    Except
    1.32
     Alas
    1.27
    Activations Density 0.861%

    No Known Activations