© 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. 22303
    Prev
    Next
    INDEX
    Explanations

    phrases related to the production company "Wong Fu"

    oai_token-act-pair · gpt-3.5-turbo

    references to "Fu."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     CES
    -0.75
     marble
    -0.73
    Scot
    -0.72
     Stranger
    -0.70
    uddle
    -0.68
    dale
    -0.67
     slip
    -0.66
     Macedonia
    -0.64
    antine
    -0.63
    Philadelphia
    -0.63
    POSITIVE LOGITS
     Fu
    3.89
    Fu
    2.96
    fu
    2.89
     fu
    2.25
    FU
    1.71
     Pu
    1.26
    fuel
    1.23
     Fei
    1.16
     Fuj
    1.12
     Fuji
    1.12
    Activations Density 0.022%

    No Known Activations