© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 17840
    Prev
    Next
    INDEX
    Explanations

    notable individuals or entities paired with actions involving recognition or acknowledgment

    oai_token-act-pair · gpt-3.5-turbo

    the preposition "of" and its associated context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    accompan
    -0.77
    assment
    -0.74
    pots
    -0.71
    obyl
    -0.70
    respective
    -0.70
    aund
    -0.69
    userc
    -0.68
    downs
    -0.66
    volume
    -0.64
    pling
    -0.64
    POSITIVE LOGITS
     course
    1.18
     Syracuse
    0.94
     Bellev
    0.94
     Philadelphia
    0.91
     Queens
    0.91
     Lebanon
    0.89
     Pennsylvania
    0.88
     Hartford
    0.87
     Rochester
    0.87
     Montreal
    0.87
    Activations Density 0.074%

    No Known Activations