© 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. 0-RES-JB
    6. 1759
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences with the word "nail" and a suggestion, followed by a progression of hitting with a hammer

    oai_token-act-pair · gpt-3.5-turbo

    instances of quotation marks or direct speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tradem
    -0.53
     adolesc
    -0.51
    ĵĺ
    -0.49
     Redmond
    -0.49
    byss
    -0.48
    guyen
    -0.48
    ĪĴ
    -0.47
    GoldMagikarp
    -0.46
    ñ
    -0.46
    senal
    -0.45
    POSITIVE LOGITS
    "
    2.74
    "-
    2.25
    "[
    2.22
    "...
    2.17
    "(
    2.14
    "?
    2.10
    "â̦
    2.10
    "'
    2.07
    %"
    2.01
    "!
    1.98
    Activations Density 0.130%

    No Known Activations