Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 19047
    Prev
    Next
    INDEX
    Explanations

    phrases related to the sky

    oai_token-act-pair · gpt-3.5-turbo

    references to the sky

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ô
    -0.84
    utic
    -0.82
    ublic
    -0.77
    atives
    -0.73
    udes
    -0.72
    icer
    -0.69
     Paste
    -0.68
    utics
    -0.67
    akeru
    -0.66
    ivities
    -0.66
    POSITIVE LOGITS
    hawk
    1.08
    watching
    1.04
    burst
    0.99
    rock
    0.97
     skies
    0.96
    beam
    0.95
    fall
    0.94
    scape
    0.91
     sky
    0.91
    walk
    0.90
    Activations Density 0.034%

    No Known Activations