© 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. 8405
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences beginning with "Apparently"

    oai_token-act-pair · gpt-3.5-turbo

    the word "apparently" and its variations used in a sentence

    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
    akable
    -0.77
    Appearances
    -0.71
    oulder
    -0.69
    igers
    -0.69
    glas
    -0.68
    allas
    -0.67
    cart
    -0.66
    aiman
    -0.66
    efer
    -0.66
    ription
    -0.64
    POSITIVE LOGITS
     unaware
    0.83
     influenced
    0.76
     forgot
    0.74
     unrelated
    0.74
     forgetting
    0.73
     incapable
    0.73
     swayed
    0.73
     oblivious
    0.69
     persuaded
    0.68
     unaffected
    0.68
    Activations Density 0.038%

    No Known Activations