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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7-RES-JB
    11. 15680
    Prev
    Next
    INDEX
    Explanations

    proper names or common nouns related to various subjects, such as sports, technology, and medicine

    oai_token-act-pair · gpt-3.5-turbo

    instances of sentences or phrases that conclude or summarize ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pooled
    -0.73
     simplicity
    -0.72
     brilliantly
    -0.72
     treadmill
    -0.72
     dominating
    -0.71
     monopol
    -0.71
     horrend
    -0.71
     loneliness
    -0.70
     pir
    -0.69
     cheaply
    -0.69
    POSITIVE LOGITS
     Additionally
    1.17
     According
    1.11
     Previously
    1.09
     Sources
    1.08
    PHOTOS
    1.07
     Tickets
    1.07
     Meanwhile
    1.04
     Officials
    1.03
     Currently
    1.01
     Possible
    1.00
    Activations Density 0.477%

    No Known Activations