© 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. 16136
    Prev
    Next
    INDEX
    Explanations

    instances of the word "plus" accompanied by specific numerical values

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "plus" and its variations, indicating an additive or cumulative context

    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
    dfx
    -0.81
    ruary
    -0.75
    adr
    -0.71
    ugu
    -0.71
    OCK
    -0.69
    utable
    -0.67
    ollar
    -0.66
    clinton
    -0.66
    abies
    -0.65
    NPR
    -0.65
    POSITIVE LOGITS
    cules
    1.02
    minus
    0.88
     bonuses
    0.75
     bonus
    0.74
    henko
    0.74
    /-
    0.73
     infinity
    0.72
     extras
    0.69
    lihood
    0.68
     assorted
    0.65
    Activations Density 0.033%

    No Known Activations