© 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. 19011
    Prev
    Next
    INDEX
    Explanations

    references to the popular online game "War.io"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "io"

    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
     abiding
    -0.70
     mans
    -0.67
     refuge
    -0.66
     land
    -0.66
     tresp
    -0.65
     cottage
    -0.62
     marked
    -0.60
     dispel
    -0.60
     shr
    -0.60
     sneaking
    -0.59
    POSITIVE LOGITS
    io
    4.28
    ios
    2.58
    IO
    2.55
    iol
    1.78
    ius
    1.60
    iano
    1.59
    iot
    1.58
    iod
    1.54
    iop
    1.53
    iov
    1.52
    Activations Density 0.013%

    No Known Activations