© 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 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. 0-RES-JB
    11. 12554
    Prev
    Next
    INDEX
    Explanations

    instances of the name "Juanita"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "ita" or its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     circuits
    -0.65
     engineered
    -0.64
     bits
    -0.62
     brokers
    -0.62
     circ
    -0.61
     dial
    -0.60
     factories
    -0.58
     tracking
    -0.57
     Cycl
    -0.57
    builders
    -0.57
    POSITIVE LOGITS
    ita
    4.37
    itas
    2.40
    ito
    1.75
    itta
    1.38
    itia
    1.34
    itar
    1.31
    itan
    1.25
    anda
    1.22
    eta
    1.21
    itate
    1.21
    Activations Density 0.006%

    No Known Activations