© 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. 6-RES-JB
    11. 10956
    Prev
    Next
    INDEX
    Explanations

    verbs or verb phrases indicating future intentions or actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating an intention or necessity, particularly with the word "to."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     scares
    -0.69
    Dur
    -0.66
     spikes
    -0.65
     handles
    -0.64
     nets
    -0.61
     triggers
    -0.61
     fires
    -0.61
     axes
    -0.61
     doesnt
    -0.60
     Appears
    -0.60
    POSITIVE LOGITS
    asted
    1.03
    lled
    0.98
    wered
    0.96
    asting
    0.95
    othy
    0.94
    pless
    0.94
    asters
    0.92
    asty
    0.91
    ilet
    0.88
    haps
    0.87
    Activations Density 0.108%

    No Known Activations