© 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. 7-RES-JB
    6. 2931
    Prev
    Next
    INDEX
    Explanations

    punctuation symbols

    oai_token-act-pair · gpt-3.5-turbo

    formatting symbols and parentheses in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    edi
    -0.76
    izz
    -0.76
    vale
    -0.74
    alian
    -0.73
    iera
    -0.72
     grocer
    -0.71
    yll
    -0.67
    alia
    -0.67
    bern
    -0.65
    angan
    -0.65
    POSITIVE LOGITS
    ãĤ´ãĥ³
    0.88
     Includes
    0.82
     [+
    0.78
     Prot
    0.73
     Ibid
    0.71
     Whoever
    0.71
     Parables
    0.70
     APPLIC
    0.69
     Benef
    0.68
     Ensure
    0.68
    Activations Density 0.040%

    No Known Activations