© 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
    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. 10969
    Prev
    Next
    INDEX
    Explanations

    names of individuals, particularly those involved in political or media contexts

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of the name "Walsh" and associated contexts

    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
    ifying
    -0.86
    ifier
    -0.85
    ified
    -0.83
    ifiers
    -0.81
    acular
    -0.76
    aining
    -0.74
    ific
    -0.71
    ifies
    -0.69
    ained
    -0.68
    alion
    -0.68
    POSITIVE LOGITS
    urst
    0.82
    patrick
    0.79
    gaard
    0.79
    hower
    0.74
    intosh
    0.72
    ufact
    0.71
     AFB
    0.71
    sth
    0.68
    enegger
    0.68
    gren
    0.68
    Activations Density 0.063%

    No Known Activations