© 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. 0-RES-JB
    11. 22752
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific company and product names

    oai_token-act-pair · gpt-3.5-turbo

    references to specific brands, businesses, or figures associated with those brands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wcs
    -0.78
     Pog
    -0.76
    天
    -0.71
    capacity
    -0.71
    ç
    -0.67
    IQ
    -0.67
    éĸ
    -0.67
    tics
    -0.67
    ihar
    -0.66
    ongo
    -0.66
    POSITIVE LOGITS
     Trader
    2.76
     Macy
    1.50
     Uncle
    1.33
     Sally
    1.32
     Aunt
    1.16
     sheriff
    1.08
    aminer
    1.01
     Trad
    0.99
     Midnight
    0.95
     Papa
    0.93
    Activations Density 0.072%

    No Known Activations