© 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 EvalsExportsinterp-engineNEWAPI 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. 8-RES-JB
    11. 12417
    Prev
    Next
    INDEX
    Explanations

    abbreviations, acronyms, or alternative names for concepts

    oai_token-act-pair · gpt-3.5-turbo

    the word "or" and its frequency in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olicy
    -0.76
    rue
    -0.75
    erest
    -0.73
    irms
    -0.71
    arten
    -0.70
    axies
    -0.70
    obile
    -0.70
    estern
    -0.69
    eor
    -0.69
    ires
    -0.69
    POSITIVE LOGITS
    chard
    0.93
     alternatively
    0.89
    ifice
    0.88
    acles
    0.80
     equival
    0.80
    chid
    0.80
    chest
    0.78
    acle
    0.76
     equivalent
    0.75
     whatever
    0.71
    Activations Density 0.077%

    No Known Activations