© 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. 19095
    Prev
    Next
    INDEX
    Explanations

    instances where a task or action is mentioned as being done or addressed at a later time

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "later."

    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
     Pwr
    -0.92
    Merit
    -0.77
     Haram
    -0.65
    Pri
    -0.65
    mad
    -0.65
    toe
    -0.64
    efe
    -0.63
    HY
    -0.63
    KN
    -0.61
    Ble
    -0.61
    POSITIVE LOGITS
    ally
    1.09
     generations
    0.99
     stages
    0.90
     phases
    0.89
    iations
    0.88
     batches
    0.87
     installments
    0.84
     iterations
    0.83
    ality
    0.82
     versions
    0.82
    Activations Density 0.036%

    No Known Activations