© 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. 6871
    Prev
    Next
    INDEX
    Explanations

    names of news organizations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of news articles or news outlets

    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
    aterasu
    -0.71
     metallic
    -0.66
     Elys
    -0.65
     pairs
    -0.63
     dotted
    -0.63
     ceilings
    -0.62
     carp
    -0.62
     dra
    -0.62
     cel
    -0.61
     ceiling
    -0.61
    POSITIVE LOGITS
     News
    3.59
    News
    2.65
     NEWS
    2.32
    news
    2.28
     news
    2.08
    NEWS
    1.94
     Newspaper
    1.53
     Newsp
    1.47
     Journalists
    1.41
     Journalism
    1.39
    Activations Density 0.016%

    No Known Activations