© 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. 1948
    Prev
    Next
    INDEX
    Explanations

    phrases related to quantity or amount

    oai_token-act-pair · gpt-3.5-turbo

    quantitative assessments involving numbers and factors

    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
    gypt
    -0.78
    Cola
    -0.75
    ebook
    -0.75
     Vide
    -0.70
    ecake
    -0.70
    aline
    -0.70
    ĸļ
    -0.70
    aeus
    -0.67
     Sans
    -0.67
    hua
    -0.67
    POSITIVE LOGITS
     factors
    1.70
     aspects
    1.60
     considerations
    1.46
     assumptions
    1.40
     safeguards
    1.38
     conditions
    1.37
     reasons
    1.37
     facets
    1.35
     measures
    1.34
     variables
    1.33
    Activations Density 0.392%

    No Known Activations