© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 1658
    Prev
    Next
    INDEX
    Explanations

    instances where an action is already completed or in progress

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "already."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    case
    -0.87
    udge
    -0.85
    rent
    -0.79
    rus
    -0.73
    istics
    -0.71
    ueller
    -0.70
    rary
    -0.69
    rarily
    -0.68
    ger
    -0.66
    onnaissance
    -0.66
    POSITIVE LOGITS
     underway
    0.95
     exists
    0.85
     existed
    0.85
     surpassed
    0.85
     booked
    0.83
     knew
    0.80
     begun
    0.78
     exist
    0.76
     racked
    0.75
     accounted
    0.75
    Activations Density 0.032%

    No Known Activations