© 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. 6283
    Prev
    Next
    INDEX
    Explanations

    names of various places and people mixed with details of events or situations involving them

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "the" and its frequency in various contexts

    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
     âĢº
    -0.85
    nav
    -0.81
    ibaba
    -0.81
    joice
    -0.77
     namely
    -0.77
    buster
    -0.75
    âĦ¢:
    -0.74
    govtrack
    -0.72
    Tier
    -0.69
    replace
    -0.68
    POSITIVE LOGITS
     latter
    1.13
     slightest
    1.13
     entirety
    1.06
     youngest
    1.03
     same
    0.99
     remainder
    0.94
     ensuing
    0.93
     ordeal
    0.91
     idea
    0.90
     onset
    0.90
    Activations Density 0.697%

    No Known Activations