© 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. 10-RES-JB
    11. 3183
    Prev
    Next
    INDEX
    Explanations

    nicknames or aliases that people are known by

    oai_token-act-pair · gpt-3.5-turbo

    mentions of nicknames or alternate names associated with individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    azaki
    -0.82
    existing
    -0.72
    ittal
    -0.70
    SPONSORED
    -0.69
    yrim
    -0.68
    usable
    -0.66
    Constructed
    -0.66
    ensing
    -0.65
    urches
    -0.65
    ynski
    -0.64
    POSITIVE LOGITS
     "
    1.03
     "#
    0.98
     '
    0.94
     Operation
    0.94
     "'
    0.93
     Punch
    0.93
     Bloody
    0.84
     ''
    0.84
     Fancy
    0.81
     ``
    0.81
    Activations Density 0.106%

    No Known Activations