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

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 22589
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "volume" or related derivatives

    oai_token-act-pair · gpt-3.5-turbo

    references to quantity or volume

    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
     Ritual
    -0.75
     Dream
    -0.70
     Shining
    -0.68
    Ranked
    -0.68
     Nightmare
    -0.67
     Cere
    -0.65
    NRS
    -0.65
     Rite
    -0.64
     Legions
    -0.62
     Registered
    -0.61
    POSITIVE LOGITS
     hun
    0.94
    leys
    0.91
     vol
    0.85
    otaur
    0.84
    uin
    0.80
    sels
    0.79
    eenth
    0.77
    tesy
    0.76
    itably
    0.75
     awa
    0.73
    Activations Density 0.009%

    No Known Activations