© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 14133
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "white"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "whit" and variations related to it

    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
    raltar
    -0.85
    ournal
    -0.78
    Reference
    -0.77
    Population
    -0.76
    UTION
    -0.76
    GS
    -0.71
    displayText
    -0.69
    HAM
    -0.69
    PsyNetMessage
    -0.67
    ROM
    -0.66
    POSITIVE LOGITS
     whit
    1.20
    ewater
    1.13
    elist
    1.00
    eness
    0.94
    ening
    0.93
    ened
    0.82
    ener
    0.81
    clus
    0.77
    etooth
    0.76
    estone
    0.75
    Activations Density 0.005%

    No Known Activations