© 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. 0-RES-JB
    11. 8257
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "cel" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    terms related to cellular technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     heads
    -0.68
     Heads
    -0.66
     necks
    -0.61
     Hitman
    -0.61
     ups
    -0.61
     accounts
    -0.60
     SNAP
    -0.60
     pres
    -0.60
     Wa
    -0.59
     UNHCR
    -0.59
    POSITIVE LOGITS
    cel
    4.82
    cell
    1.46
    ce
    1.13
    cest
    1.12
    celer
    1.08
    pell
    1.08
    cer
    1.07
    cus
    1.04
    cius
    1.03
    cells
    0.98
    Activations Density 0.017%

    No Known Activations