© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2203
    Prev
    Next
    INDEX
    Explanations

    words related to the term "Dod"

    oai_token-act-pair · gpt-3.5-turbo

    names and references to specific sports teams or players

    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
    inventoryQuantity
    -0.66
    ropolitan
    -0.62
    olitan
    -0.58
    HAEL
    -0.57
     nudity
    -0.57
     mu
    -0.56
    ansion
    -0.56
    aeda
    -0.56
     charged
    -0.56
     suites
    -0.55
    POSITIVE LOGITS
    ging
    1.25
    gement
    1.23
    ges
    1.22
    gers
    1.16
    yssey
    1.11
    ger
    1.10
    ged
    1.10
    der
    1.10
    gins
    1.07
    gy
    1.07
    Activations Density 0.046%

    No Known Activations