© 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. 6495
    Prev
    Next
    INDEX
    Explanations

    words related to locations or events related to the town of Middletown

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "kid" or derivatives related to childhood

    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
     metast
    -0.65
     Aux
    -0.64
    OPLE
    -0.58
    xon
    -0.56
     flap
    -0.56
     Palm
    -0.56
     heads
    -0.55
     Situation
    -0.55
     mainland
    -0.55
     exha
    -0.54
    POSITIVE LOGITS
    eenth
    0.91
    ety
    0.87
    itional
    0.85
    lest
    0.85
    icter
    0.83
    olesc
    0.83
    escription
    0.82
    eret
    0.82
    erella
    0.82
    ish
    0.81
    Activations Density 0.032%

    No Known Activations