© 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. 3-RES-JB
    11. 1781
    Prev
    Next
    INDEX
    Explanations

    scientific family names related to biology

    oai_token-act-pair · gpt-3.5-turbo

    taxonomy-related terminology and mentions of incest

    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
     machine
    -0.77
    hand
    -0.75
     hust
    -0.74
    machine
    -0.70
     unreal
    -0.65
     Brook
    -0.63
     seam
    -0.62
     redeem
    -0.61
    steel
    -0.61
    hof
    -0.60
    POSITIVE LOGITS
    idae
    1.19
    aceae
    1.02
    Magikarp
    0.88
     Species
    0.86
    osis
    0.84
    GROUP
    0.83
    èĢħ
    0.79
    ciation
    0.78
     Parables
    0.76
    pta
    0.76
    Activations Density 0.015%

    No Known Activations