© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 21173
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "ipp" followed by a single-digit or double-digit number

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "ipp" and its various contexts and usages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Breed
    -0.79
    BuyableInstoreAndOnline
    -0.76
    QUIRE
    -0.70
     Bravo
    -0.66
     bearer
    -0.64
    =-=-=-=-
    -0.64
    FORE
    -0.63
    IZE
    -0.63
    CVE
    -0.63
    vae
    -0.63
    POSITIVE LOGITS
    ocamp
    1.31
    ipp
    1.14
    sburgh
    1.14
    oman
    0.96
    ortun
    0.96
    alon
    0.95
    onen
    0.94
    lisher
    0.92
    ulative
    0.91
    earances
    0.89
    Activations Density 0.014%

    No Known Activations