© 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. 0-RES-JB
    11. 15795
    Prev
    Next
    INDEX
    Explanations

    mentions related to fundraising or financial support

    oai_token-act-pair · gpt-3.5-turbo

    terms related to fundraising activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     atom
    -0.73
     autom
    -0.70
     Pebble
    -0.69
     compartment
    -0.68
     backend
    -0.67
     collide
    -0.67
    xes
    -0.66
     sands
    -0.66
     Yug
    -0.64
    illac
    -0.64
    POSITIVE LOGITS
    raising
    3.03
    raised
    2.20
    raise
    1.92
     Marks
    1.65
     Welch
    1.07
    ealous
    1.04
     McDonnell
    1.01
    ardon
    0.93
     Sevent
    0.90
     Raise
    0.90
    Activations Density 0.052%

    No Known Activations