© 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. 2-RES-JB
    11. 784
    Prev
    Next
    INDEX
    Explanations

    words associated with poetry and poems

    oai_token-act-pair · gpt-4-turbo

    mentions of poetry

    oai_token-act-pair · gpt-3.5-turbo

    references to poetry and poems

    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
    avez
    -0.79
    anson
    -0.78
    erate
    -0.77
    rals
    -0.71
    aryl
    -0.70
    laus
    -0.69
    ormons
    -0.68
    ormon
    -0.67
    negie
    -0.66
    orea
    -0.66
    POSITIVE LOGITS
     poetry
    1.29
     poems
    1.23
     laureate
    1.19
     poets
    1.13
     poem
    1.11
     poet
    1.03
     poetic
    0.93
    pee
    0.78
    accompan
    0.75
     festivals
    0.74
    Activations Density 0.010%

    No Known Activations