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

    Neuronpedia

    Jacobian LensNEW
    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. 8004
    Prev
    Next
    INDEX
    Explanations

    names of people

    oai_token-act-pair · gpt-3.5-turbo

    names of prominent individuals, particularly those with first and last names starting with 'Robert' or 'C' and their associated titles

    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
    vity
    -0.71
    ashtra
    -0.69
    gencies
    -0.69
    ournals
    -0.69
    yip
    -0.68
     ail
    -0.67
    ueless
    -0.66
    Marie
    -0.65
    warm
    -0.64
     PJ
    -0.62
    POSITIVE LOGITS
    lund
    0.75
    ħĭ
    0.74
    Publisher
    0.65
    Bridge
    0.65
    Ke
    0.64
    ®
    0.62
     Baird
    0.62
     Morales
    0.61
    İ
    0.60
    ipel
    0.59
    Activations Density 0.099%

    No Known Activations