© 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. 6-RES-JB
    11. 18360
    Prev
    Next
    INDEX
    Explanations

    names or terms related to a specific individual, potentially a person named Ul

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals involved in social justice or abolitionist causes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Niagara
    -0.73
    oké
    -0.72
    agne
    -0.71
     vapor
    -0.68
    ãģĨ
    -0.66
    istine
    -0.66
    ioxide
    -0.65
    BuyableInstoreAndOnline
    -0.64
    externalActionCode
    -0.63
    76561
    -0.63
    POSITIVE LOGITS
    ulum
    0.79
    reon
    0.72
    nuts
    0.70
    ITED
    0.69
    locking
    0.68
    lesiastical
    0.68
    otive
    0.68
    riks
    0.67
    uliffe
    0.65
    otor
    0.65
    Activations Density 0.065%

    No Known Activations