© 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. 7465
    Prev
    Next
    INDEX
    Explanations

    proper nouns such as names of people, organizations, and locations

    oai_token-act-pair · gpt-3.5-turbo

    references to specific organizations and institutions

    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
    =-=-=-=-
    -0.70
    bryce
    -0.62
     tomorrow
    -0.60
     beforehand
    -0.60
     ASAP
    -0.60
     recent
    -0.59
    :,
    -0.59
     particulars
    -0.59
    âĶģ
    -0.58
     complying
    -0.57
    POSITIVE LOGITS
     began
    1.14
     became
    1.14
     underwent
    1.04
     reverted
    1.03
     wrote
    1.02
     debuted
    1.01
     finally
    1.00
     abruptly
    1.00
     embarked
    0.99
     undertook
    0.98
    Activations Density 0.482%

    No Known Activations