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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 22775
    Prev
    Next
    INDEX
    Explanations

    phrases related to observatories and observations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "observatory" and closely related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Yugoslavia
    -0.68
    LOAD
    -0.68
     GDDR
    -0.64
     Mechanical
    -0.63
     Blow
    -0.62
     Soup
    -0.61
     Hearts
    -0.60
     Ply
    -0.60
     Leilan
    -0.60
    berry
    -0.59
    POSITIVE LOGITS
    atories
    1.29
    atory
    1.14
    ables
    1.11
     observ
    1.11
    ational
    0.95
    ations
    0.95
    ivities
    0.93
    omy
    0.90
    ance
    0.90
    ances
    0.88
    Activations Density 0.016%

    No Known Activations