© 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. 0-RES-JB
    11. 7755
    Prev
    Next
    INDEX
    Explanations

    keywords related to the term "hippopotamus"

    oai_token-act-pair · gpt-3.5-turbo

    references to "Hipp" or related concepts, indicating a focus on the hippie culture or themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Forge
    -0.80
     Forge
    -0.75
     Episode
    -0.75
    nder
    -0.74
    Net
    -0.73
    ovie
    -0.71
    forge
    -0.71
    bsp
    -0.71
     Blades
    -0.71
     Garland
    -0.71
    POSITIVE LOGITS
     Hipp
    3.55
     hipp
    2.92
     Arist
    1.21
     rad
    1.20
     Pyth
    1.13
     Aristotle
    1.13
     yog
    1.09
     Socrates
    0.99
     Amph
    0.98
     Athen
    0.97
    Activations Density 0.063%

    No Known Activations