© 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. 9-RES-JB
    6. 5585
    Prev
    Next
    INDEX
    Explanations

    pairs of phrases or sentences where the second phrase continues or emphasizes the argument made in the first phrase

    oai_token-act-pair · gpt-3.5-turbo

    the presence 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 @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eers
    -0.70
    olves
    -0.69
    aukee
    -0.64
    è¦ļéĨĴ
    -0.61
    igers
    -0.60
    ttes
    -0.59
    nexus
    -0.57
    zl
    -0.57
    llo
    -0.55
    ://
    -0.55
    POSITIVE LOGITS
     although
    1.06
     unlike
    1.06
     despite
    1.05
     alas
    1.00
     contrary
    1.00
    despite
    0.98
     barring
    0.92
    withstanding
    0.91
     unless
    0.91
     irrespective
    0.90
    Activations Density 0.100%

    No Known Activations