© 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. 6-RES-JB
    11. 8011
    Prev
    Next
    INDEX
    Explanations

    phrases related to general topics or themes

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases related to generalizations and overall assessments

    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
    Eva
    -0.73
    rosso
    -0.71
    hots
    -0.71
    poon
    -0.70
     ashore
    -0.70
    ONSORED
    -0.69
    utics
    -0.68
    acus
    -0.67
    thood
    -0.66
    BIL
    -0.66
    POSITIVE LOGITS
     extent
    1.02
     portion
    0.97
     nature
    0.94
    most
    0.92
     assumption
    0.92
     population
    0.91
     populace
    0.90
    liest
    0.88
     equivalent
    0.88
     opposite
    0.88
    Activations Density 0.233%

    No Known Activations