© 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. 12939
    Prev
    Next
    INDEX
    Explanations

    expressions related to personal experiences or reflections

    oai_token-act-pair · gpt-3.5-turbo

    mention of life experiences or personal reflections on life

    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
     Cosponsors
    -0.83
    EStreamFrame
    -0.77
    CAST
    -0.74
    agger
    -0.74
    mented
    -0.69
    sonian
    -0.68
     Bundy
    -0.68
    Wed
    -0.68
    uned
    -0.64
    ãĥĺ
    -0.64
    POSITIVE LOGITS
     expectancy
    0.95
    guards
    0.93
    boat
    0.86
    blood
    0.85
    boats
    0.85
     ashore
    0.82
    mares
    0.81
    sole
    0.80
    lier
    0.80
    guard
    0.80
    Activations Density 0.038%

    No Known Activations