© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 9508
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Lee" followed by a number that decreases slightly with each activation

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of the name "Lee" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orate
    -0.69
    ancial
    -0.66
     CPC
    -0.65
    rices
    -0.63
     Obesity
    -0.63
    achu
    -0.61
    onut
    -0.60
     Beir
    -0.59
    icals
    -0.59
     Cosponsors
    -0.59
    POSITIVE LOGITS
    lee
    1.19
    pless
    0.92
    arthed
    0.86
    scill
    0.83
    lees
    0.82
    ce
    0.81
    witz
    0.81
    gha
    0.80
    velength
    0.80
    heed
    0.79
    Activations Density 0.009%

    No Known Activations