© 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. 1-RES-JB
    11. 22684
    Prev
    Next
    INDEX
    Explanations

    phrases related to searching or exploring

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "bing."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     breeze
    -0.71
    oret
    -0.63
     cover
    -0.59
    262
    -0.58
     foundation
    -0.57
    GN
    -0.56
     pronounced
    -0.56
     scrimmage
    -0.56
    aternity
    -0.56
     understandable
    -0.55
    POSITIVE LOGITS
    bing
    1.47
    redients
    0.92
    interstitial
    0.89
    lehem
    0.85
    staking
    0.84
    bery
    0.79
    HAM
    0.79
    wana
    0.79
    phrine
    0.78
    ling
    0.78
    Activations Density 0.014%

    No Known Activations