© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 10019
    Prev
    Next
    INDEX
    Explanations

    politicians and political figures

    oai_token-act-pair · gpt-3.5-turbo

    closing punctuation marks in lists or enumerations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rogens
    -0.80
    romeda
    -0.70
    ral
    -0.67
    zers
    -0.67
    endo
    -0.66
    aban
    -0.65
    ton
    -0.63
    ku
    -0.63
    rogen
    -0.63
    arna
    -0.62
    POSITIVE LOGITS
     Flavoring
    0.66
    ordable
    0.65
    channelAvailability
    0.62
    ————
    0.62
     comprising
    0.60
    agascar
    0.59
    anship
    0.59
     which
    0.59
     implying
    0.57
     namely
    0.57
    Activations Density 0.096%

    No Known Activations