© 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. 2-RES-JB
    11. 15500
    Prev
    Next
    INDEX
    Explanations

    words related to grilling or barbecue

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of the prefix "gr" that precede various words

    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
    vention
    -0.76
    phrine
    -0.75
    )=(
    -0.74
    hibition
    -0.70
    tics
    -0.65
    ĸļ
    -0.64
    doors
    -0.61
     vitro
    -0.61
    eers
    -0.61
    66666666
    -0.60
    POSITIVE LOGITS
    aciously
    1.07
    umpy
    1.03
    iffin
    1.02
    ands
    0.99
    acies
    0.97
    udge
    0.96
    asp
    0.94
    udging
    0.91
    iddle
    0.90
    ained
    0.87
    Activations Density 0.006%

    No Known Activations