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. 11132
    Prev
    Next
    INDEX
    Explanations

    references to a specific entity, in this case, various lineups or lists involving different contexts such as music festivals and product offerings

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "lineup" in various contexts, indicating its focus on groups or collections, particularly in entertainment or product settings

    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
    nai
    -0.96
    birth
    -0.89
    hig
    -0.82
    ricular
    -0.75
    ryn
    -0.73
    imb
    -0.73
    bara
    -0.71
    versely
    -0.70
    mit
    -0.69
    ilit
    -0.67
    POSITIVE LOGITS
     lineup
    1.07
     XI
    0.86
     choices
    0.73
    ttes
    0.73
     swaps
    0.72
     XV
    0.71
     favourites
    0.66
     assignments
    0.66
     selections
    0.65
     scrimmage
    0.65
    Activations Density 0.008%

    No Known Activations