© 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. 9-RES-JB
    11. 8974
    Prev
    Next
    INDEX
    Explanations

    simple phrases containing the word "that" or "it"

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to technological processes or operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cth
    -0.46
     Churchill
    -0.45
     Piper
    -0.45
     Lann
    -0.44
    OF
    -0.44
     Messiah
    -0.44
     Wool
    -0.43
     Mechdragon
    -0.43
     Pascal
    -0.43
     Rey
    -0.43
    POSITIVE LOGITS
    rils
    0.57
    cery
    0.55
    versible
    0.55
    moil
    0.51
    bole
    0.49
    cffffcc
    0.49
    ASY
    0.48
    inki
    0.48
    idation
    0.48
    ily
    0.47
    Activations Density 1.639%

    No Known Activations