© 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. 11-RES-JB
    11. 10168
    Prev
    Next
    INDEX
    Explanations

    technological terms and items related to governance and military activities

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include conjunctions linking multiple items or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amera
    -0.70
    nikov
    -0.67
     Register
    -0.67
     Michaels
    -0.63
    yout
    -0.62
     Tycoon
    -0.62
    uliffe
    -0.61
     ($)
    -0.58
    mson
    -0.58
    aez
    -0.58
    POSITIVE LOGITS
     other
    0.88
     related
    0.80
     oun
    0.75
     Other
    0.67
     similar
    0.65
     adjoining
    0.62
     elsewhere
    0.62
     referen
    0.61
     ensuing
    0.60
    OTHER
    0.57
    Activations Density 0.237%

    No Known Activations