© 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. 8460
    Prev
    Next
    INDEX
    Explanations

    terms related to legal actions and confiscation of items or property

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the seizure or removal of property, especially in a legal or punitive context

    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
    GROUND
    -0.74
    terday
    -0.71
    xual
    -0.68
    grass
    -0.66
     Maid
    -0.66
    BRE
    -0.63
    WAYS
    -0.62
    WER
    -0.61
     fed
    -0.61
     expectancy
    -0.60
    POSITIVE LOGITS
    ator
    0.98
    ation
    0.95
    otics
    0.95
    ities
    0.93
    atory
    0.92
    ount
    0.92
    ij
    0.92
    ateur
    0.90
    alities
    0.89
    ographs
    0.89
    Activations Density 0.043%

    No Known Activations