© 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. 9548
    Prev
    Next
    INDEX
    Explanations

    mentions of physical objects

    oai_token-act-pair · gpt-3.5-turbo

    references to physical or conceptual "units" in various contexts

    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
     Marketable
    -0.76
    aukee
    -0.72
    NetMessage
    -0.71
    vous
    -0.67
     straw
    -0.66
    å¦
    -0.65
    é»Ĵ
    -0.65
     Earthqu
    -0.65
    gian
    -0.64
    etsk
    -0.64
    POSITIVE LOGITS
    mates
    1.02
    mate
    1.00
     unit
    0.95
     units
    0.94
    unit
    0.92
    units
    0.90
    imet
    0.88
    Unit
    0.87
    arily
    0.86
    matically
    0.84
    Activations Density 0.011%

    No Known Activations