© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 23327
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific name or theme, potentially with variations in spelling

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "gog" or related terms in the context of specific subjects

    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
     demand
    -0.69
     reception
    -0.69
     relations
    -0.68
     momentum
    -0.65
     Taxi
    -0.61
     deadline
    -0.61
     commitment
    -0.61
     foundations
    -0.60
     infrastructure
    -0.60
     approach
    -0.60
    POSITIVE LOGITS
    ogg
    4.77
    oggles
    1.69
    oggle
    1.51
    wav
    1.35
    ogs
    1.29
    og
    1.24
    ugg
    1.23
    ogle
    1.18
    OG
    1.09
    ripp
    1.09
    Activations Density 0.012%

    No Known Activations