© 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. 6-RES-JB
    11. 11598
    Prev
    Next
    INDEX
    Explanations

    images or mentions of cats, especially kittens

    oai_token-act-pair · gpt-3.5-turbo

    references to cats and kittens

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    unda
    -0.84
     Petroleum
    -0.76
    eous
    -0.74
    ioxide
    -0.69
     GOODMAN
    -0.68
     Sachs
    -0.68
    indal
    -0.66
    nce
    -0.65
    ijn
    -0.63
    states
    -0.63
    POSITIVE LOGITS
     kittens
    1.01
     paws
    1.00
     kitten
    0.97
     pets
    0.96
     paw
    0.92
     puppies
    0.91
     euth
    0.86
     zoo
    0.86
     cats
    0.86
     grooming
    0.84
    Activations Density 0.068%

    No Known Activations