© 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. 2-RES-JB
    11. 12748
    Prev
    Next
    INDEX
    Explanations

    highly relevant words related to patterns, trends, or recurring behaviors

    oai_token-act-pair · gpt-3.5-turbo

    terms related to trends or trend-related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OTOS
    -0.65
    aiman
    -0.65
     Kaufman
    -0.62
    OPS
    -0.62
    keley
    -0.61
    avez
    -0.60
    ategory
    -0.60
    berman
    -0.58
     ashes
    -0.58
    uana
    -0.58
    POSITIVE LOGITS
    ezvous
    1.58
    rend
    1.32
    erer
    1.16
    eering
    1.06
    erers
    0.97
    ered
    0.89
    lyn
    0.88
    ing
    0.86
    icator
    0.85
    ers
    0.85
    Activations Density 0.008%

    No Known Activations