Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 17644
    Prev
    Next
    INDEX
    Explanations

    mentions of meetings involving specific individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to political meetings involving Russian officials and potential collusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Jagu
    -0.93
     Municip
    -0.91
     relegation
    -0.88
     ILCS
    -0.87
    liga
    -0.85
     ç¥ŀ
    -0.84
     Horses
    -0.79
     Cure
    -0.79
     masc
    -0.79
     Riding
    -0.78
    POSITIVE LOGITS
     CIA
    1.45
    CIA
    1.34
    FBI
    1.29
     intelligence
    1.26
     FBI
    1.25
     FISA
    1.19
     NSA
    1.19
    intelligence
    1.19
    ionage
    1.18
     briefed
    1.17
    Activations Density 1.484%

    No Known Activations