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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 24531
    Prev
    Next
    INDEX
    Explanations

    code comments

    oai_token-act-pair · gpt-3.5-turbo

    comments or annotations in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ylum
    -0.92
    vertisement
    -0.83
    ogy
    -0.81
    edom
    -0.81
     tsunami
    -0.77
     fractures
    -0.76
    xual
    -0.74
    issance
    -0.73
     satell
    -0.72
    ocratic
    -0.71
    POSITIVE LOGITS
    ////////////////////////////////
    1.28
    ////////////////
    1.22
    ////////
    1.20
    ================================================================
    1.13
    ++++++++++++++++
    1.10
     ----------------------------------------------------------------
    1.06
     =================================================================
    1.01
     ********************************
    0.94
    ================================
    0.93
    ********************************
    0.93
    Activations Density 0.011%

    No Known Activations