© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 23553
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases indicating the benefits or consequences of specific actions

    oai_token-act-pair · gpt-3.5-turbo

    statements about benefits or positive effects associated with various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cles
    -0.72
    rose
    -0.68
    venants
    -0.67
    Mah
    -0.65
    phant
    -0.64
    $,
    -0.64
    rette
    -0.63
    }{
    -0.62
    sponsored
    -0.62
    Sold
    -0.62
    POSITIVE LOGITS
    geries
    0.98
     purposes
    0.86
    gotten
    0.83
     example
    0.83
    agers
    0.82
     laughs
    0.79
     everybody
    0.77
     detecting
    0.77
     reasons
    0.75
     starters
    0.75
    Activations Density 0.087%

    No Known Activations