© 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. 1110
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "bie" or "bies"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "bie" or its variations within the text

    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
     centers
    -0.64
     reconstructed
    -0.64
     precipitation
    -0.62
     governors
    -0.58
    æĪ
    -0.58
     thus
    -0.58
     transc
    -0.58
     panels
    -0.58
     Pacers
    -0.56
     ox
    -0.56
    POSITIVE LOGITS
    bie
    4.56
    bies
    3.22
    bee
    1.39
    bish
    1.16
    bys
    1.14
    bery
    1.08
    zee
    1.06
    loo
    1.06
    bey
    1.06
    bi
    1.04
    Activations Density 0.016%

    No Known Activations