© 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. 4-RES-JB
    11. 19888
    Prev
    Next
    INDEX
    Explanations

    words containing the specific substring "ipp"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the "ipp" sequence, indicating an emphasis on particular names or entities

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

    No Comments

    Negative Logits
    BuyableInstoreAndOnline
    -0.71
     Bravo
    -0.69
    CVE
    -0.66
     Breed
    -0.66
    vae
    -0.65
    Downloadha
    -0.64
     Labyrinth
    -0.63
    netflix
    -0.63
    tumblr
    -0.63
    #$
    -0.63
    POSITIVE LOGITS
    ocamp
    1.31
    sburgh
    1.12
    ortun
    0.99
    erton
    0.97
    onent
    0.93
    eco
    0.92
    earance
    0.91
    etitive
    0.90
    ipp
    0.89
    itude
    0.88
    Activations Density 0.008%

    No Known Activations