© 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. 11-RES-JB
    11. 783
    Prev
    Next
    INDEX
    Explanations

    words related to celebrations and commemorations

    oai_token-act-pair · gpt-3.5-turbo

    references to celebrations and commemorations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sway
    -0.64
     brute
    -0.63
     somew
    -0.63
    URE
    -0.61
     influence
    -0.61
     pitch
    -0.60
     algorithms
    -0.60
     sol
    -0.60
     containment
    -0.59
     saline
    -0.59
    POSITIVE LOGITS
    brate
    1.29
    br
    1.16
    brates
    1.13
    ative
    1.03
    orical
    1.01
    gments
    0.99
    ptive
    0.99
    oric
    0.98
    apolis
    0.98
    ased
    0.97
    Activations Density 0.076%

    No Known Activations