© 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. 8-RES-JB
    11. 7726
    Prev
    Next
    INDEX
    Explanations

    directional instructions and spatial relationships

    oai_token-act-pair · gpt-3.5-turbo

    references to direction and gender distinctions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    edIn
    -0.65
    conservancy
    -0.65
    odka
    -0.64
    abo
    -0.62
    allo
    -0.61
    LES
    -0.61
    ©¶æ¥µ
    -0.60
    NRS
    -0.60
    ivated
    -0.58
     sclerosis
    -0.57
    POSITIVE LOGITS
     versus
    1.25
     vs
    1.18
    /-
    0.99
    -,
    0.92
     or
    0.90
    /
    0.90
     and
    0.89
     AND
    0.84
    ->
    0.83
     ->
    0.82
    Activations Density 0.473%

    No Known Activations