© 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. 8-RES-JB
    11. 17248
    Prev
    Next
    INDEX
    Explanations

    verbs indicating the ability to perform an action or the impossibility of an action

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing limitations or prohibitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rongh
    -0.62
     assorted
    -0.60
    leted
    -0.58
    ghan
    -0.58
     mull
    -0.57
     rather
    -0.56
    rather
    -0.56
     unsurprisingly
    -0.56
    ischer
    -0.55
    JO
    -0.54
    POSITIVE LOGITS
     anymore
    1.39
     nor
    1.06
     unless
    0.89
     anything
    0.88
    urate
    0.85
     adequately
    0.85
     anywhere
    0.79
     anybody
    0.79
     coherent
    0.78
     satisf
    0.78
    Activations Density 0.352%

    No Known Activations