Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 5672
    Prev
    Next
    INDEX
    Explanations

    I'm sorry, but I couldn't find a clear pattern in the activations provided for neuron 4 to give a summary

    oai_token-act-pair · gpt-3.5-turbo

    references to "stuff" in a variety of contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    emale
    -0.77
    vette
    -0.69
    bern
    -0.69
    deen
    -0.68
    stal
    -0.68
    HCR
    -0.66
    CVE
    -0.65
    INAL
    -0.65
    pent
    -0.65
    glas
    -0.65
    POSITIVE LOGITS
    bags
    1.01
     happening
    0.90
     happens
    0.87
    hots
    0.85
    iness
    0.83
     sack
    0.79
    bag
    0.79
    ious
    0.78
     else
    0.76
    herer
    0.75
    Activations Density 0.031%

    No Known Activations