© 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. 0-RES-JB
    11. 2806
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'nylon'

    oai_token-act-pair · gpt-3.5-turbo

    references to nylon materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iment
    -0.72
     privilege
    -0.68
    osit
    -0.64
    change
    -0.64
    formation
    -0.63
    occ
    -0.63
    opathy
    -0.63
     tempt
    -0.62
    ness
    -0.61
    fect
    -0.60
    POSITIVE LOGITS
     nylon
    1.15
    ©¶æ¥µ
    0.79
    Rated
    0.74
    hiba
    0.73
    çķ
    0.73
    hester
    0.72
     Sloan
    0.72
    taboola
    0.71
     Valiant
    0.70
    payer
    0.69
    Activations Density 0.000%

    No Known Activations