© 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. 8-RES-JB
    11. 9043
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to various individuals

    oai_token-act-pair · gpt-3.5-turbo

    the word "who," indicating references to individuals or characters 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
     VIDEOS
    -0.69
     Checking
    -0.66
     Watching
    -0.65
    BOX
    -0.65
    PD
    -0.64
     Anyway
    -0.64
     Confederation
    -0.62
    Loading
    -0.62
    Okay
    -0.61
    AGES
    -0.61
    POSITIVE LOGITS
     specializes
    1.11
     frequ
    1.04
     resided
    1.02
     oversaw
    1.00
     thri
    0.99
     fought
    0.98
     lived
    0.98
     wears
    0.98
     overcame
    0.97
     wore
    0.95
    Activations Density 0.118%

    No Known Activations