© 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. 10-RES-JB
    11. 10191
    Prev
    Next
    INDEX
    Explanations

    locations or places based on the names mentioned

    oai_token-act-pair · gpt-3.5-turbo

    geographical locations and affiliations

    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
    merce
    -0.80
    votes
    -0.75
    acca
    -0.75
    ebin
    -0.69
    onym
    -0.69
    aukee
    -0.66
     lying
    -0.65
    nings
    -0.64
     Crimea
    -0.64
    subject
    -0.63
    POSITIVE LOGITS
     Symphony
    0.95
    based
    0.94
     entrepreneur
    0.93
     based
    0.89
     natives
    0.86
     Consulting
    0.84
     headquartered
    0.81
     native
    0.81
     Dynamics
    0.81
     Instruments
    0.79
    Activations Density 0.200%

    No Known Activations