© 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. 7-RES-JB
    11. 2052
    Prev
    Next
    INDEX
    Explanations

    links to URLs and filenames in a computer-related context

    oai_token-act-pair · gpt-3.5-turbo

    URLs and links related to various online resources

    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
    abal
    -0.78
    ï¸ı
    -0.71
    rament
    -0.66
    xit
    -0.65
     Bung
    -0.64
    oglu
    -0.64
    retty
    -0.62
     Lauderdale
    -0.61
    Vs
    -0.60
    orem
    -0.60
    POSITIVE LOGITS
    wealth
    0.72
    ĨĴ
    0.72
    ij士
    0.69
    çİĭ
    0.69
    trade
    0.66
    library
    0.64
    ĸ
    0.63
    º
    0.63
    common
    0.63
    çīĪ
    0.62
    Activations Density 0.142%

    No Known Activations