© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 11582
    Prev
    Next
    INDEX
    Explanations

    terms related to economic activities and public issues

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and references to evidence or statistics

    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
     Firstly
    -0.52
     Slightly
    -0.51
    ?,
    -0.51
    Picture
    -0.50
    PLIED
    -0.49
    >,
    -0.48
    jab
    -0.48
     -->
    -0.46
    onen
    -0.46
    tackle
    -0.45
    POSITIVE LOGITS
    cellaneous
    0.77
     thereafter
    0.75
     accordingly
    0.64
     thereof
    0.64
     therein
    0.61
     importantly
    0.60
     afterward
    0.60
     respectively
    0.58
    ).[
    0.56
    etooth
    0.56
    Activations Density 1.778%

    No Known Activations