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. 1-RES-JB
    6. 14641
    Prev
    Next
    INDEX
    Explanations

    references to the term "TW" or "Thames" which could be associated with a specific topic or entity

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific television network or media outlet

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    netflix
    -0.96
    hammad
    -0.89
    lain
    -0.82
    eer
    -0.82
    backer
    -0.81
    resso
    -0.79
    eering
    -0.79
    ering
    -0.77
     Hamm
    -0.77
    gio
    -0.76
    POSITIVE LOGITS
     TW
    1.14
    TW
    1.08
    BUR
    0.88
     GOODMAN
    0.82
    ©¶æ¥µ
    0.82
     redund
    0.80
    pez
    0.79
    DEV
    0.78
    OY
    0.78
    seys
    0.72
    Activations Density 0.013%

    No Known Activations