© 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. 7027
    Prev
    Next
    INDEX
    Explanations

    technical specifications and measurements

    oai_token-act-pair · gpt-3.5-turbo

    information related to numerical data and measurements

    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
     paving
    -0.59
     solicit
    -0.59
     purportedly
    -0.57
     appell
    -0.56
     amid
    -0.56
     allegedly
    -0.56
     inform
    -0.56
     unwittingly
    -0.55
     stewards
    -0.54
     indis
    -0.54
    POSITIVE LOGITS
     max
    0.88
     avg
    0.81
     lvl
    0.80
    RGB
    0.79
     +/-
    0.77
    medium
    0.75
    lvl
    0.74
     Medium
    0.74
    max
    0.73
     1440
    0.72
    Activations Density 0.566%

    No Known Activations