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. 9-RES-JB
    6. 93
    Prev
    Next
    INDEX
    Explanations

    mentions of astronomy-related terms and concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to astrobiology or related scientific topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ipal
    -0.76
    ãģĭ
    -0.70
    ãĥ¯
    -0.66
    BACK
    -0.65
    igham
    -0.62
    ãĥ¬
    -0.62
    士
    -0.61
     Hearts
    -0.60
     possession
    -0.60
     trickle
    -0.59
    POSITIVE LOGITS
    roph
    1.37
    igmat
    1.25
    rology
    1.25
    rolog
    1.22
    ral
    1.17
    rament
    1.17
    rob
    1.14
    rop
    1.14
    rog
    1.13
    ron
    1.12
    Activations Density 0.030%

    No Known Activations