© 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. 3-RES-JB
    11. 665
    Prev
    Next
    INDEX
    Explanations

    references to a slot, specifically in the context of sports or technology

    oai_token-act-pair · gpt-3.5-turbo

    references to slot positions or roles in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    externalActionCode
    -0.65
     Pyr
    -0.63
    ĨĴ
    -0.62
    kj
    -0.62
    omen
    -0.62
     Wheat
    -0.60
     Edmund
    -0.60
    harm
    -0.60
    vironment
    -0.59
     Beacon
    -0.58
    POSITIVE LOGITS
     slots
    1.10
     slot
    1.06
    tery
    1.01
    Slot
    1.00
    ting
    0.84
    ular
    0.83
    slot
    0.82
    ulously
    0.81
     Slot
    0.81
    otom
    0.81
    Activations Density 0.013%

    No Known Activations