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

    Neuronpedia

    Jacobian LensNEW
    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. 9-RES-JB
    11. 20028
    Prev
    Next
    INDEX
    Explanations

    phrases indicating some kind of action or event that is about to happen

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "to" indicating intentions or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     expecting
    -0.79
    Reviewer
    -0.77
     lucky
    -0.76
     tasked
    -0.74
     tweeting
    -0.72
     wishes
    -0.72
     expects
    -0.71
     oversaw
    -0.70
     hoping
    -0.70
     preparing
    -0.70
    POSITIVE LOGITS
     occur
    1.46
     unfold
    1.21
     happen
    1.20
     arise
    1.19
     expire
    1.19
     explode
    1.18
     affect
    1.11
     exist
    1.10
     vanish
    1.10
     coincide
    1.08
    Activations Density 0.283%

    No Known Activations