© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 17753
    Prev
    Next
    INDEX
    Explanations

    descriptions or mentions of puppies

    oai_token-act-pair · gpt-3.5-turbo

    mentions of puppies or related terms in the text

    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
    ibur
    -0.83
    NetMessage
    -0.74
    aea
    -0.74
    ORGE
    -0.73
    lor
    -0.73
     Lank
    -0.72
    rooms
    -0.69
    abor
    -0.68
    ribe
    -0.68
    mberg
    -0.67
    POSITIVE LOGITS
     puppy
    1.11
     puppies
    1.02
     Pupp
    0.99
     retri
    0.97
     kitten
    0.83
     pup
    0.81
     kittens
    0.73
     retrie
    0.73
    rador
    0.73
     Humane
    0.72
    Activations Density 0.016%

    No Known Activations