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. 4-RES-JB
    6. 23438
    Prev
    Next
    INDEX
    Explanations

    words related to hard work or effort

    oai_token-act-pair · gpt-3.5-turbo

    words related to the process of tiling

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

    No Comments

    Negative Logits
    axter
    -0.86
    orers
    -0.84
     ende
    -0.84
     unden
    -0.82
    ¥ŀ
    -0.80
    yssey
    -0.75
    uther
    -0.71
    osate
    -0.70
    orer
    -0.70
    ĵĺ
    -0.69
    POSITIVE LOGITS
    ptin
    0.79
    nah
    0.68
    balls
    0.65
    lust
    0.64
    mma
    0.64
    ball
    0.64
    Steam
    0.63
    mate
    0.62
     ashes
    0.61
    paces
    0.61
    Activations Density 0.012%

    No Known Activations