© 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. 2765
    Prev
    Next
    INDEX
    Explanations

    links to websites

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and web links in the text

    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
    ©¶æ
    -0.94
    »Ĵ
    -0.79
    anooga
    -0.78
    Ļ½
    -0.76
     behavi
    -0.72
    bably
    -0.72
    oshenko
    -0.70
     motorists
    -0.70
    ¯¯
    -0.69
    ¥ŀ
    -0.69
    POSITIVE LOGITS
    com
    1.03
    amazon
    1.01
    esp
    1.00
    facebook
    0.99
    debian
    0.99
    example
    0.98
    info
    0.97
    cdn
    0.95
    youtube
    0.95
    google
    0.95
    Activations Density 0.104%

    No Known Activations