© 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. 3-RES-JB
    11. 4287
    Prev
    Next
    INDEX
    Explanations

    instances of the word "carbon"

    oai_token-act-pair · gpt-3.5-turbo

    references to carbon compounds and their role in various processes

    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
    DragonMagazine
    -0.83
    GBT
    -0.81
    HCR
    -0.80
     Psychiatric
    -0.76
    akings
    -0.76
    ":["
    -0.76
    VERTIS
    -0.73
    ERY
    -0.72
    Attempts
    -0.71
    ---------------
    -0.71
    POSITIVE LOGITS
     dioxide
    1.55
     emissions
    1.04
    ohydrate
    1.04
     fibre
    0.98
     emission
    0.98
     footprint
    0.92
     fiber
    0.92
     carbon
    0.89
     nitrogen
    0.85
     gases
    0.84
    Activations Density 0.014%

    No Known Activations