© 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. 4-RES-JB
    6. 20549
    Prev
    Next
    INDEX
    Explanations

    descriptive words emphasizing intensity or value

    oai_token-act-pair · gpt-3.5-turbo

    emphasis on intensity or frequency of certain experiences or feelings

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

    No Comments

    Negative Logits
    endants
    -0.84
    endant
    -0.72
    mere
    -0.70
    iddler
    -0.68
    iere
    -0.66
    rift
    -0.65
    iers
    -0.63
    reen
    -0.62
    pent
    -0.62
    rehens
    -0.61
    POSITIVE LOGITS
     darn
    0.98
     Funny
    0.83
     bye
    0.80
     gotta
    0.77
     nice
    0.77
    ãĤ´ãĥ³
    0.77
     fun
    0.77
     damn
    0.76
     Helpful
    0.76
     blah
    0.76
    Activations Density 0.283%

    No Known Activations