© 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. 9-RES-JB
    11. 9839
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions or interactions

    oai_token-act-pair · gpt-3.5-turbo

    past tense verbs that indicate actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Located
    -0.66
     stockpile
    -0.64
    ta
    -0.63
     guiActiveUnfocused
    -0.62
     Seeking
    -0.57
     Birthday
    -0.57
    made
    -0.55
     Own
    -0.55
     Inher
    -0.54
     Bought
    -0.54
    POSITIVE LOGITS
     conclusions
    0.85
    Discussion
    0.83
    question
    0.82
    atform
    0.80
     insight
    0.80
     conclusion
    0.79
     unequiv
    0.78
     assertions
    0.75
     insights
    0.75
     concluding
    0.74
    Activations Density 0.322%

    No Known Activations