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. 0-RES-JB
    6. 17609
    Prev
    Next
    INDEX
    Explanations

    phrases related to observatories or scientific research locations

    oai_token-act-pair · gpt-3.5-turbo

    references to observatories and expressions of disapproval

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atin
    -0.73
    SW
    -0.65
    chuk
    -0.65
     |--
    -0.65
    Mobil
    -0.65
    TPP
    -0.64
     ide
    -0.64
    sand
    -0.64
    vas
    -0.63
    HTML
    -0.63
    POSITIVE LOGITS
     disappro
    2.24
     observ
    2.23
     disapproval
    1.92
     Observatory
    1.86
     disapprove
    1.77
     Observ
    1.08
     Sta
    1.04
     expressive
    0.99
     viewpoint
    0.98
     Barney
    0.95
    Activations Density 0.036%

    No Known Activations