© 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. 6-RES-JB
    6. 17340
    Prev
    Next
    INDEX
    Explanations

    quotations within text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of commas in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erity
    -0.62
     Settlement
    -0.59
    Holy
    -0.57
     seams
    -0.57
    proof
    -0.57
    Next
    -0.57
     trouble
    -0.56
    Maker
    -0.56
    DonaldTrump
    -0.55
    irie
    -0.55
    POSITIVE LOGITS
     adding
    1.13
     referring
    1.01
     citing
    1.00
     noting
    0.98
     echoing
    0.97
     quoting
    0.93
     recalling
    0.91
     emphasizing
    0.91
     stressing
    0.87
     albeit
    0.85
    Activations Density 0.123%

    No Known Activations