© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2798
    Prev
    Next
    INDEX
    Explanations

    questions beginning with the word "What"

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of a specific prompt or formatting element

    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
    atory
    -0.64
    heter
    -0.63
    MER
    -0.58
    shore
    -0.58
    general
    -0.58
    hig
    -0.57
    ¯
    -0.57
    stretched
    -0.57
    ULT
    -0.57
    witch
    -0.56
    POSITIVE LOGITS
    soever
    1.28
     happens
    1.12
     Makes
    1.09
     Happ
    1.03
     distinguishes
    1.01
     happened
    1.01
     constitutes
    0.96
     Lies
    0.96
     separates
    0.96
     transpired
    0.95
    Activations Density 0.073%

    No Known Activations