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. 3-RES-JB
    6. 18674
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or events that occur and are reported as happening

    oai_token-act-pair · gpt-3.5-turbo

    punctuational transitions that emphasize ongoing thoughts or clauses in a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adelphia
    -0.82
    ascar
    -0.74
     Serie
    -0.68
    ás
    -0.67
    Correct
    -0.64
    imum
    -0.63
    ÃŃa
    -0.63
     Liga
    -0.59
    izon
    -0.59
    urst
    -0.59
    POSITIVE LOGITS
     alike
    1.04
     consequently
    1.01
     thereof
    0.85
     accordingly
    0.85
     importantly
    0.85
     consequ
    0.79
     succeeded
    0.79
     thereafter
    0.77
     subsequent
    0.76
     secondly
    0.76
    Activations Density 1.214%

    No Known Activations