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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 10-RES-JB
    11. 18779
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by locations or organizations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "in"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    casters
    -0.59
     therein
    -0.55
     [*
    -0.53
    —"
    -0.51
    rible
    -0.50
    ãĤ£
    -0.49
     importantly
    -0.49
    Though
    -0.49
    Meanwhile
    -0.49
     surpr
    -0.48
    POSITIVE LOGITS
    clusions
    0.92
     lieu
    0.87
    clus
    0.85
     vitro
    0.79
     favour
    0.79
    breeding
    0.78
    humane
    0.78
    bred
    0.78
     conjunction
    0.74
     accordance
    0.74
    Activations Density 0.246%

    No Known Activations