© 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. 4-RES-JB
    11. 6561
    Prev
    Next
    INDEX
    Explanations

    names related to the word "Foster"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Foster" in various contexts

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

    No Comments

    Negative Logits
    uyomi
    -0.79
    orem
    -0.69
    aution
    -0.68
    hang
    -0.68
     reneg
    -0.67
    hare
    -0.66
    ngth
    -0.65
    pers
    -0.64
    Magikarp
    -0.64
    realDonaldTrump
    -0.63
    POSITIVE LOGITS
     Foster
    0.87
     Farms
    0.86
    wolves
    0.80
     Dull
    0.78
    lements
    0.78
    gart
    0.75
     Cust
    0.73
    ieri
    0.72
    BALL
    0.70
    lings
    0.70
    Activations Density 0.007%

    No Known Activations