Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 9640
    Prev
    Next
    INDEX
    Explanations

    contractions in sentences

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating certainty or obligation

    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
    atl
    -0.74
     Hass
    -0.69
    rawdownloadcloneembedreportprint
    -0.65
    tsky
    -0.63
     Collider
    -0.60
     Malays
    -0.59
    OTOS
    -0.58
    kin
    -0.57
     Clause
    -0.56
     hijab
    -0.56
    POSITIVE LOGITS
     likely
    1.07
     automatically
    0.96
     surely
    0.93
     probably
    0.91
     invariably
    0.89
     certainly
    0.87
     inevitably
    0.87
     immediately
    0.85
     usually
    0.84
     undoubtedly
    0.84
    Activations Density 0.352%

    No Known Activations