© 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. 10-RES-JB
    11. 4855
    Prev
    Next
    INDEX
    Explanations

    references or citations indicated by the term "Ref"

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ciating
    -0.73
    daq
    -0.71
    ;;;;;;;;;;;;
    -0.68
    ITIES
    -0.64
     Manhattan
    -0.64
     atmosphere
    -0.63
    DAQ
    -0.63
    teenth
    -0.63
    Īè
    -0.62
     Tsarnaev
    -0.62
    POSITIVE LOGITS
    eree
    1.52
    lections
    1.50
    lection
    1.49
    riger
    1.43
    eren
    1.41
    lected
    1.40
    erences
    1.38
    lect
    1.30
    uge
    1.29
    erred
    1.28
    Activations Density 0.017%

    No Known Activations