© 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. 6893
    Prev
    Next
    INDEX
    Explanations

    formats consistent with TV show or movie titles

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols in the text

    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
    inator
    -0.70
    ¿½
    -0.69
    allel
    -0.68
    unia
    -0.64
    Ĥ¬
    -0.61
     abundance
    -0.61
    Ń
    -0.60
    imon
    -0.59
    inators
    -0.59
    orf
    -0.58
    POSITIVE LOGITS
     (*
    0.68
    tm
    0.68
    catentry
    0.66
    Deal
    0.65
    #$
    0.61
    Math
    0.60
     sheet
    0.60
    berra
    0.58
    ();
    0.57
     olds
    0.57
    Activations Density 0.049%

    No Known Activations