© 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. 10-RES-JB
    11. 18491
    Prev
    Next
    INDEX
    Explanations

    locations and names of people or places mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to homes or residences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     type
    -0.56
     kinds
    -0.55
     Helpful
    -0.55
     experien
    -0.52
     Directory
    -0.52
     dos
    -0.52
    ochem
    -0.52
     types
    -0.51
     UD
    -0.51
     nice
    -0.51
    POSITIVE LOGITS
    âĢ
    1.31
    îĢ
    1.06
     âĢ
    1.04
    âĸł
    1.00
    «
    0.99
    âĹı
    0.96
    »
    0.93
    âĢł
    0.92
    [/
    0.90
    **
    0.86
    Activations Density 1.030%

    No Known Activations