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. 3-RES-JB
    6. 19514
    Prev
    Next
    INDEX
    Explanations

    terms related to circulation, such as blood circulation or currency circulation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to circulation and its associated concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RAG
    -0.82
    ofi
    -0.75
    ermott
    -0.68
    oug
    -0.68
    IELD
    -0.66
    omething
    -0.66
    este
    -0.65
    oeuv
    -0.64
    imus
    -0.63
    ASC
    -0.63
    POSITIVE LOGITS
     circulation
    1.36
     advis
    0.85
     receipts
    0.79
     diffusion
    0.78
    irtual
    0.78
     circ
    0.75
     circulate
    0.74
     mathemat
    0.74
    icter
    0.72
     trough
    0.70
    Activations Density 0.009%

    No Known Activations