© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2-RES-JB
    11. 9383
    Prev
    Next
    INDEX
    Explanations

    the specific word "dozens"

    oai_token-act-pair · gpt-3.5-turbo

    references to large quantities or groups, specifically the word "dozens."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Dub
    -0.61
    mediate
    -0.61
     illum
    -0.60
     fixation
    -0.59
    sole
    -0.59
     Lover
    -0.58
     symmetry
    -0.57
    estamp
    -0.57
     Om
    -0.56
    ppers
    -0.56
    POSITIVE LOGITS
    uously
    0.87
     Dozens
    0.83
    dozen
    0.83
     thousand
    0.81
     dozen
    0.79
     thousands
    0.79
     dozens
    0.77
    ourcing
    0.77
    paces
    0.76
    hovah
    0.76
    Activations Density 0.005%

    No Known Activations