© 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. 4-RES-JB
    11. 10123
    Prev
    Next
    INDEX
    Explanations

    words related to medical conditions characterized as not severe

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "mild" and its variations

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

    No Comments

    Negative Logits
    andise
    -0.83
     Store
    -0.70
     Yards
    -0.70
    atography
    -0.67
    miah
    -0.66
    ilater
    -0.66
    berus
    -0.64
     Markets
    -0.63
     Dame
    -0.63
    ynthesis
    -0.62
    POSITIVE LOGITS
    er
    1.10
    est
    1.08
    ew
    0.98
    erate
    0.94
    ers
    0.91
    ening
    0.88
    ener
    0.84
    ened
    0.84
     annoyance
    0.81
    ering
    0.79
    Activations Density 0.007%

    No Known Activations