© 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 EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 18336
    Prev
    Next
    INDEX
    Explanations

    proper nouns like names and brand names

    oai_token-act-pair · gpt-3.5-turbo

    references to specific names and terms related to particular brands or concepts, particularly 'Neo', 'Neon', 'Omni', and 'Robo'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¼ãĤ¦ãĤ¹
    -0.81
    Reviewer
    -0.78
    tons
    -0.77
    rawdownloadcloneembedreportprint
    -0.76
    ional
    -0.73
    loo
    -0.73
    rier
    -0.73
    staking
    -0.72
    tub
    -0.72
    à¨
    -0.71
    POSITIVE LOGITS
     Geo
    0.97
    XT
    0.80
     Neo
    0.78
     Pok
    0.78
     Zero
    0.77
     Lumpur
    0.77
    arthed
    0.75
     Scotia
    0.72
    pheus
    0.69
    lect
    0.69
    Activations Density 0.014%

    No Known Activations