© 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. 11451
    Prev
    Next
    INDEX
    Explanations

    mentions of newspapers and specific news articles

    oai_token-act-pair · gpt-3.5-turbo

    mentions of newspapers

    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
    aves
    -0.79
    arius
    -0.64
    mentation
    -0.62
    max
    -0.61
    AMD
    -0.61
     ±
    -0.61
     Reson
    -0.60
    factor
    -0.60
    yth
    -0.60
    flows
    -0.60
    POSITIVE LOGITS
     newspaper
    3.44
     newspapers
    2.62
     Newspaper
    2.58
     tabloid
    1.94
     magazine
    1.81
     Newsp
    1.78
     paper
    1.65
     journal
    1.54
     papers
    1.54
     publication
    1.53
    Activations Density 0.015%

    No Known Activations