© 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. 2-RES-JB
    11. 15938
    Prev
    Next
    INDEX
    Explanations

    proper nouns ending in 'na'

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific topic or entity, likely related to a name or organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    =-=-=-=-
    -0.78
     Cosponsors
    -0.75
    tails
    -0.73
     UID
    -0.72
    RFC
    -0.70
    library
    -0.68
    tracks
    -0.67
    utenberg
    -0.66
    starter
    -0.66
    papers
    -0.65
    POSITIVE LOGITS
    eus
    1.20
    uthor
    1.08
    ïve
    1.00
    veland
    0.98
    wn
    0.96
    isance
    0.96
    ples
    0.95
    vel
    0.91
    uth
    0.90
    ñ
    0.88
    Activations Density 0.008%

    No Known Activations