© 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. 9-RES-JB
    11. 17418
    Prev
    Next
    INDEX
    Explanations

    list or rank items, often with a superlative descriptor like "top" or "best"

    oai_token-act-pair · gpt-3.5-turbo

    references to popular rankings or "top" lists

    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
    ĸļ
    -0.83
    ighter
    -0.78
    adra
    -0.76
    hyde
    -0.76
    atum
    -0.74
    ctor
    -0.69
    strength
    -0.69
    matter
    -0.68
    riber
    -0.68
    icum
    -0.68
    POSITIVE LOGITS
     moments
    1.11
     quotes
    1.10
     stories
    0.99
     locations
    0.94
     places
    0.93
     examples
    0.93
     intersections
    0.93
     unsolved
    0.92
     topics
    0.91
     websites
    0.90
    Activations Density 0.201%

    No Known Activations