© 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. 7-RES-JB
    11. 21596
    Prev
    Next
    INDEX
    Explanations

    instructions for cooking in an oven

    oai_token-act-pair · gpt-3.5-turbo

    empty segments or delimiters in 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
    _.
    -0.50
     versa
    -0.49
    ogether
    -0.48
     UNCLASSIFIED
    -0.47
    }.
    -0.47
    ļéĨĴ
    -0.46
    jri
    -0.46
    pled
    -0.44
    acly
    -0.43
     territ
    -0.43
    POSITIVE LOGITS
     Belfast
    0.57
     Donald
    0.49
     Transgender
    0.48
     NRL
    0.47
     Hillary
    0.46
     Brisbane
    0.45
     cyclist
    0.44
     Sask
    0.44
    ONDON
    0.44
     Toronto
    0.44
    Activations Density 1.436%

    No Known Activations