© 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. 6-RES-JB
    11. 17460
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "erk"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific software tool or framework

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eur
    -0.69
    lli
    -0.66
    ILA
    -0.64
     wid
    -0.63
    é¾įåĸļ士
    -0.61
     fortun
    -0.61
     Mayweather
    -0.59
     Mith
    -0.59
    inals
    -0.58
     focal
    -0.58
    POSITIVE LOGITS
    olk
    0.91
    steen
    0.90
    lass
    0.90
    owsky
    0.88
    owitz
    0.86
    inki
    0.86
    lund
    0.86
    wagen
    0.84
    kamp
    0.84
    heimer
    0.82
    Activations Density 0.037%

    No Known Activations