© 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. 8770
    Prev
    Next
    INDEX
    Explanations

    words related to loud vocal expressions of emotion such as screaming, yelling, and moaning

    oai_token-act-pair · gpt-3.5-turbo

    references to vocal expressions of emotion or distress

    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
    folios
    -0.79
    biased
    -0.78
    ravel
    -0.72
    livious
    -0.71
    bably
    -0.71
    omaly
    -0.66
    mun
    -0.66
    vertisements
    -0.66
    dating
    -0.66
    smoking
    -0.65
    POSITIVE LOGITS
     scream
    1.00
     screams
    0.91
     Vera
    0.80
     aloud
    0.78
     Scream
    0.77
     louder
    0.77
     screamed
    0.76
    terday
    0.76
     yells
    0.75
    inx
    0.75
    Activations Density 0.014%

    No Known Activations