© 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. 17493
    Prev
    Next
    INDEX
    Explanations

    mentions of specific instances or occurrences of events

    oai_token-act-pair · gpt-3.5-turbo

    instances of personal experiences or first-time occurrences

    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
     accordingly
    -0.78
     therefore
    -0.70
    then
    -0.68
     meantime
    -0.64
     secondly
    -0.60
     furthermore
    -0.60
     nevertheless
    -0.60
    doms
    -0.59
    clusions
    -0.59
     abound
    -0.59
    POSITIVE LOGITS
     ever
    0.97
     EVER
    0.93
    ever
    0.88
     bothered
    0.79
     interacted
    0.78
     encount
    0.77
     heard
    0.77
     touched
    0.77
     ventured
    0.75
     interfered
    0.74
    Activations Density 0.191%

    No Known Activations