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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-RES-JB
    6. 20221
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to various entertainment media productions

    oai_token-act-pair · gpt-3.5-turbo

    titles or terms associated with various forms of entertainment or media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cellaneous
    -0.73
    Wilson
    -0.66
    Jimmy
    -0.63
    icial
    -0.62
    qua
    -0.61
    ©¶æ¥µ
    -0.61
    fitting
    -0.61
    dozen
    -0.61
    amous
    -0.61
    ordinate
    -0.61
    POSITIVE LOGITS
     aims
    0.98
     embodies
    0.97
     represents
    0.97
     revolves
    0.96
     differs
    0.95
     solves
    0.95
     focuses
    0.95
     succeeds
    0.94
     consists
    0.93
     combines
    0.91
    Activations Density 0.220%

    No Known Activations