© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4-RES-JB
    11. 17162
    Prev
    Next
    INDEX
    Explanations

    website URLs

    oai_token-act-pair · gpt-3.5-turbo

    instances of web links or URLs

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

    No Comments

    Negative Logits
    ©¶æ
    -0.85
    anooga
    -0.84
    »Ĵ
    -0.78
    ¯¯
    -0.77
    ħĭ
    -0.76
    ãĥ¼ãĥĨ
    -0.75
    ĪĴ
    -0.74
    Ļ½
    -0.69
    aukee
    -0.69
     guiActiveUn
    -0.68
    POSITIVE LOGITS
    facebook
    1.17
    youtube
    1.09
    example
    0.99
    daily
    0.99
    amazon
    0.96
    esp
    0.96
    archives
    0.95
    com
    0.91
    gov
    0.91
    design
    0.91
    Activations Density 0.047%

    No Known Activations