© 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. 2979
    Prev
    Next
    INDEX
    Explanations

    instances of a specific word or name, "Barn" or "Barnet."

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific place or location

    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
    ctors
    -0.77
    ffic
    -0.76
     Garc
    -0.66
    aneous
    -0.63
    utenant
    -0.62
    terday
    -0.60
    VICE
    -0.60
     Nare
    -0.59
    ittee
    -0.59
     regret
    -0.59
    POSITIVE LOGITS
    acles
    1.36
    acle
    1.27
    yard
    1.24
    aby
    1.19
    owitz
    1.01
    ards
    1.00
    ues
    0.99
    ard
    0.99
    storm
    0.98
    esville
    0.97
    Activations Density 0.038%

    No Known Activations