© 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. 21736
    Prev
    Next
    INDEX
    Explanations

    phrases related to immediate actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the timing of actions or events, particularly the word "soon."

    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
    olor
    -0.71
    İĭ
    -0.70
    atively
    -0.68
    senal
    -0.67
    atives
    -0.64
    ativity
    -0.64
    avorite
    -0.64
    pel
    -0.60
    ribe
    -0.60
    cious
    -0.58
    POSITIVE LOGITS
    aneously
    0.90
     thereafter
    0.83
     afterwards
    0.72
    idious
    0.72
    eners
    0.72
    ipal
    0.69
    ening
    0.68
     realised
    0.68
    itude
    0.65
     afterward
    0.63
    Activations Density 0.009%

    No Known Activations