© 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. 8-RES-JB
    11. 6284
    Prev
    Next
    INDEX
    Explanations

    code snippets containing variable declarations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that pose conditions or questions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .''
    -0.69
    .</
    -0.65
     ..."
    -0.60
    .''.
    -0.60
     âĢİ
    -0.58
     ''
    -0.58
    .")
    -0.56
    --
    -0.53
    ''.
    -0.52
    .<
    -0.52
    POSITIVE LOGITS
    ilst
    0.56
     secondly
    0.53
     furthermore
    0.52
     Lets
    0.52
    odore
    0.51
    prisingly
    0.51
     however
    0.51
     Interesting
    0.51
    ccording
    0.51
     meanwhile
    0.51
    Activations Density 1.582%

    No Known Activations