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

    Neuronpedia

    APICircuit 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. 23952
    Prev
    Next
    INDEX
    Explanations

    specific instances or events

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases that emphasize the concept of "that" in various contexts

    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
    <?
    -0.71
    ãĤ¤ãĥĪ
    -0.70
    mobi
    -0.69
    Ø©
    -0.68
    bourg
    -0.67
     Staples
    -0.63
     reiterate
    -0.62
    ãĥĩãĤ£
    -0.62
    âķIJ
    -0.62
    ateral
    -0.61
    POSITIVE LOGITS
     arrived
    0.86
     slightest
    0.78
     arrives
    0.77
     resumed
    0.74
     disemb
    0.71
    pressed
    0.71
     arrive
    0.67
     enters
    0.67
     attacked
    0.66
    apsed
    0.64
    Activations Density 0.311%

    No Known Activations