© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 6862
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of circulation or circularity

    oai_token-act-pair · gpt-3.5-turbo

    references to circular themes or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IELD
    -0.83
    DS
    -0.73
     Scotia
    -0.69
    culosis
    -0.69
    ECH
    -0.69
    uca
    -0.68
    ARP
    -0.66
    WARD
    -0.65
     Mandela
    -0.65
    BIL
    -0.64
    POSITIVE LOGITS
    uits
    1.18
    uit
    1.12
    umn
    1.01
    adian
    0.99
    uitous
    0.96
    circ
    0.94
    ulatory
    0.89
    umb
    0.87
    onduct
    0.86
    scrib
    0.86
    Activations Density 0.021%

    No Known Activations