© 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. 11485
    Prev
    Next
    INDEX
    Explanations

    references to a specific news outlet, "Tribune"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Tribune."

    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
    pop
    -0.66
     gal
    -0.65
    åIJ
    -0.65
     thr
    -0.64
    egal
    -0.61
    go
    -0.61
    inv
    -0.61
     GB
    -0.61
    lessly
    -0.61
    pal
    -0.61
    POSITIVE LOGITS
     Tribune
    4.29
    ribune
    1.97
     Chronicle
    1.27
     Herald
    1.21
     Gazette
    1.17
     Globe
    1.14
     Newspaper
    1.11
     Observer
    1.08
     Sentinel
    1.07
     Trib
    1.01
    Activations Density 0.014%

    No Known Activations