© 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. 4-RES-JB
    11. 14692
    Prev
    Next
    INDEX
    Explanations

    names of individuals with similarities to "Kadour" or "Kad" in them

    oai_token-act-pair · gpt-3.5-turbo

    the name "Kad" along with other similar names related to individuals

    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
     Oaks
    -0.78
    helle
    -0.77
    ider
    -0.74
    oise
    -0.72
    iste
    -0.71
     Constantin
    -0.67
    ipher
    -0.66
    clerosis
    -0.64
    icol
    -0.64
    UES
    -0.63
    POSITIVE LOGITS
    doms
    0.94
    ibaba
    0.75
    ritz
    0.71
    liga
    0.68
    pad
    0.67
    yrus
    0.66
    eless
    0.66
    gap
    0.65
    anish
    0.65
    ahar
    0.64
    Activations Density 0.017%

    No Known Activations