© 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. 2-RES-JB
    11. 23700
    Prev
    Next
    INDEX
    Explanations

    specific names that include the word "wither"

    oai_token-act-pair · gpt-3.5-turbo

    forms of the word "either."

    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
     Polo
    -0.69
     exception
    -0.66
     privilege
    -0.65
     guid
    -0.63
     privileged
    -0.61
     Reneg
    -0.59
     Fukushima
    -0.58
     Redemption
    -0.57
     conqu
    -0.57
    hibition
    -0.57
    POSITIVE LOGITS
    sburg
    1.31
    soever
    1.21
    ither
    1.09
    theless
    1.01
    apy
    0.98
    cott
    0.87
    apist
    0.84
    rils
    0.83
    umbnails
    0.83
    ithing
    0.82
    Activations Density 0.006%

    No Known Activations