© 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. 1537
    Prev
    Next
    INDEX
    Explanations

    the word "to" at a high activation level

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express opportunities or permissions

    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
    due
    -0.64
     Rahman
    -0.64
     Advertisement
    -0.63
    enance
    -0.62
    audi
    -0.62
     Current
    -0.61
    payment
    -0.60
     incoming
    -0.59
    going
    -0.59
     Else
    -0.58
    POSITIVE LOGITS
     grips
    1.26
    asted
    0.92
     hear
    0.91
     know
    0.84
     see
    0.84
     choose
    0.82
    axy
    0.81
     enjoy
    0.80
     explore
    0.79
     crawl
    0.79
    Activations Density 0.040%

    No Known Activations