© 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. 1-RES-JB
    11. 16774
    Prev
    Next
    INDEX
    Explanations

    mentions of 'ribbons' and related terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to "bonds" or financial investments

    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
    XY
    -0.83
    UC
    -0.83
     McCl
    -0.72
    CV
    -0.72
    WN
    -0.72
    ORY
    -0.70
    IFE
    -0.68
    EG
    -0.67
     Kot
    -0.66
    PN
    -0.64
    POSITIVE LOGITS
    bons
    1.35
    hops
    1.35
    htaking
    1.17
    wana
    1.16
    yip
    1.11
    hips
    1.09
    poons
    1.07
    ettings
    1.04
    ertodd
    1.01
    ervatives
    0.97
    Activations Density 0.012%

    No Known Activations