Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 16569
    Prev
    Next
    INDEX
    Explanations

    words related to topics like 'killing', 'ool', 'atar', 'x', 'aser', 'aren', 'iller', 'enn', 'urd', 'istan', 'ore', 'erb', 'il', 'ner', 'iss', 'ait', 'lyn', 'ait'

    oai_token-act-pair · gpt-3.5-turbo

    words related to the term "kill" and its derivatives

    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
    ascript
    -0.82
    å°Ĩ
    -0.73
     crack
    -0.67
    VERTISEMENT
    -0.66
     span
    -0.65
    Versions
    -0.63
    nces
    -0.62
     millisec
    -0.61
    ruciating
    -0.59
    tyard
    -0.59
    POSITIVE LOGITS
    ikuman
    0.99
     Lumpur
    0.93
    lyak
    0.92
    boxing
    0.89
    arts
    0.89
    atri
    0.88
    waukee
    0.84
    enei
    0.82
    EStreamFrame
    0.82
    EStream
    0.80
    Activations Density 0.237%

    No Known Activations