© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 16233
    Prev
    Next
    INDEX
    Explanations

    scientific or technical terms related to biology or DNA

    oai_token-act-pair · gpt-3.5-turbo

    terms related to scientific skepticism and local cultural references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GES
    -0.65
    ħĭ
    -0.65
     Seas
    -0.64
     Called
    -0.62
    911
    -0.62
    _(
    -0.61
     Persons
    -0.60
     Mug
    -0.60
    ospital
    -0.60
    chell
    -0.59
    POSITIVE LOGITS
     goodness
    1.26
     firepower
    1.20
     stuff
    1.15
     crap
    1.14
     goodies
    1.10
     chatter
    1.09
     nonsense
    1.08
     clutter
    1.08
     baggage
    1.08
    stuff
    1.06
    Activations Density 0.542%

    No Known Activations