© 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. 1-RES-JB
    11. 24267
    Prev
    Next
    INDEX
    Explanations

    instances of dogs barking

    oai_token-act-pair · gpt-3.5-turbo

    topics related to the concept of stray animals and their behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lain
    -0.80
    icist
    -0.76
    HCR
    -0.74
    ̶
    -0.72
    utral
    -0.69
     GOODMAN
    -0.67
    hum
    -0.66
    ingen
    -0.66
    CBC
    -0.66
    zyme
    -0.65
    POSITIVE LOGITS
     stray
    1.13
    odox
    0.80
    bilt
    0.76
     flock
    0.73
    bats
    0.73
     dogs
    0.72
     barking
    0.71
     pup
    0.70
     dog
    0.70
     hairs
    0.70
    Activations Density 0.012%

    No Known Activations