© 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. 3-RES-JB
    11. 7794
    Prev
    Next
    INDEX
    Explanations

    articles in a written text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Article" followed by a number

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ITH
    -0.86
    adows
    -0.85
    aukee
    -0.85
    ascus
    -0.73
    eco
    -0.72
    inav
    -0.72
    awar
    -0.72
    oles
    -0.71
    escal
    -0.70
    aunder
    -0.70
    POSITIVE LOGITS
     Continued
    0.96
    ICLE
    0.92
     Articles
    0.90
    Header
    0.85
    Article
    0.84
     ARTICLE
    0.78
     Consent
    0.78
     Says
    0.74
     Article
    0.74
    meal
    0.72
    Activations Density 0.007%

    No Known Activations