© 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. 1-RES-JB
    11. 16354
    Prev
    Next
    INDEX
    Explanations

    phrases related to cosmology and the vastness of the universe

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of the universe

    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
    imar
    -0.75
    NetMessage
    -0.71
    rib
    -0.70
    iov
    -0.68
    amina
    -0.68
    dm
    -0.67
    agged
    -0.67
    ients
    -0.66
    drawn
    -0.66
    maid
    -0.63
    POSITIVE LOGITS
     universe
    0.97
    arium
    0.88
    eers
    0.85
    ĸļ
    0.82
    ichick
    0.82
     continuum
    0.82
    adelphia
    0.79
     Reborn
    0.77
    ulously
    0.75
     universes
    0.74
    Activations Density 0.012%

    No Known Activations