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

    Neuronpedia

    Jacobian LensNEW
    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. 9-RES-JB
    11. 19798
    Prev
    Next
    INDEX
    Explanations

    references to customization, especially in the context of technology or products

    oai_token-act-pair · gpt-3.5-turbo

    references to customization or personalized options

    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
    trump
    -0.78
    common
    -0.77
     CrossRef
    -0.75
    xual
    -0.74
    Æ
    -0.69
    went
    -0.67
    SEE
    -0.67
    robe
    -0.66
    doi
    -0.66
    loo
    -0.66
    POSITIVE LOGITS
    isable
    1.76
    izations
    1.72
    izable
    1.57
    ised
    1.50
    isations
    1.48
    isation
    1.42
    arily
    1.34
    ization
    1.26
    izing
    1.19
    ized
    1.18
    Activations Density 0.042%

    No Known Activations