© 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. 9-RES-JB
    11. 18463
    Prev
    Next
    INDEX
    Explanations

    references to a specific entity or brand named "Del."

    oai_token-act-pair · gpt-3.5-turbo

    references to the entity "Del" or variations thereof

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SHIP
    -0.67
     AFL
    -0.65
    OLOGY
    -0.62
     CPI
    -0.60
     altogether
    -0.60
     Moonlight
    -0.59
    beans
    -0.59
     actionGroup
    -0.59
     Authorization
    -0.58
    é¾įå¥ij士
    -0.57
    POSITIVE LOGITS
    ayed
    1.29
    icate
    1.28
    phi
    1.25
    usional
    1.23
    ivered
    1.22
    iber
    1.16
    gado
    1.15
    uxe
    1.12
    aware
    1.12
    ivery
    1.11
    Activations Density 0.023%

    No Known Activations