© 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. 7-RES-JB
    11. 19214
    Prev
    Next
    INDEX
    Explanations

    mentions of specific geopolitical entities

    oai_token-act-pair · gpt-3.5-turbo

    the definite article "the."

    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
    *,
    -0.71
    *
    -0.69
    cially
    -0.67
    tackle
    -0.66
    âĸł
    -0.65
    cture
    -0.65
     according
    -0.64
    âĢł
    -0.64
    âĿ
    -0.62
    ****
    -0.62
    POSITIVE LOGITS
     ensuing
    1.21
     rest
    1.11
     remainder
    1.11
     resultant
    1.09
     entirety
    1.02
     entire
    1.00
     aftermath
    0.98
     resulting
    0.97
     whole
    0.97
     accompanying
    0.96
    Activations Density 0.152%

    No Known Activations