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. 121
    Prev
    Next
    INDEX
    Explanations

    phrases related to philosophical or inspirational quotes

    oai_token-act-pair · gpt-3.5-turbo

    symbols and punctuation marks, particularly ones that convey emphasis or separation in quotations

    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
    otin
    -0.76
     auxiliary
    -0.76
     permits
    -0.74
     retrieval
    -0.74
     conver
    -0.73
     protective
    -0.73
     transpl
    -0.73
     circulation
    -0.73
    userc
    -0.72
     machinery
    -0.71
    POSITIVE LOGITS
    Anonymous
    1.18
    Wilson
    1.04
    Leon
    1.03
     Rapp
    1.03
    Thomas
    1.02
    George
    1.01
    Albert
    1.00
     Ibid
    0.99
    Jess
    0.98
    Bern
    0.98
    Activations Density 0.089%

    No Known Activations