© 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. 0-RES-JB
    11. 16458
    Prev
    Next
    INDEX
    Explanations

    instances of the letter 'W'

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     crore
    -0.66
    Interstitial
    -0.65
     centr
    -0.64
    uality
    -0.64
    ãĥķãĤ©
    -0.61
    jriwal
    -0.61
    anos
    -0.61
    agher
    -0.61
    ictions
    -0.59
    igraph
    -0.58
    POSITIVE LOGITS
     W
    3.08
    W
    2.12
     w
    1.61
    w
    1.55
     WM
    1.38
     Wis
    1.35
     WT
    1.34
     WA
    1.32
     WB
    1.31
    Ws
    1.27
    Activations Density 0.027%

    No Known Activations