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

    Neuronpedia

    Jacobian LensNEW
    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. 20777
    Prev
    Next
    INDEX
    Explanations

    phrases related to size, measurements, and dimensions

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and associated phrases describing measurements or characteristics

    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
    ievers
    -0.80
    roo
    -0.76
    anamo
    -0.74
    quished
    -0.73
     Alone
    -0.72
    sbm
    -0.69
    stown
    -0.68
    puter
    -0.68
    KEN
    -0.68
    idav
    -0.67
    POSITIVE LOGITS
     breadth
    1.47
     complexity
    1.42
     severity
    1.42
     depth
    1.36
     intensity
    1.36
     sophistication
    1.32
     thickness
    1.32
     width
    1.32
     size
    1.30
     length
    1.28
    Activations Density 0.233%

    No Known Activations