© 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. 10024
    Prev
    Next
    INDEX
    Explanations

    promotional content about a magazine subscription

    oai_token-act-pair · gpt-3.5-turbo

    subscription-related phrases and calls to action

    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
    axter
    -0.66
     Dame
    -0.66
    ynthesis
    -0.61
     princ
    -0.60
     Tanaka
    -0.59
     Olsen
    -0.59
    ansson
    -0.59
     Noble
    -0.58
    zona
    -0.58
    apon
    -0.58
    POSITIVE LOGITS
    Learn
    0.98
    Submit
    0.89
    Trend
    0.86
    Please
    0.85
    Feel
    0.84
    Latest
    0.80
    MED
    0.80
    Download
    0.80
    Subscribe
    0.79
    Prev
    0.79
    Activations Density 0.067%

    No Known Activations