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. 11861
    Prev
    Next
    INDEX
    Explanations

    numerical tallies or counts

    oai_token-act-pair · gpt-3.5-turbo

    references to counts or numerical tallies

    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
    NetMessage
    -0.58
     hunger
    -0.57
     Spit
    -0.57
    uve
    -0.57
     relations
    -0.56
     friendly
    -0.56
    Study
    -0.56
    choice
    -0.56
    ña
    -0.55
     interrogation
    -0.55
    POSITIVE LOGITS
     tally
    1.05
    enance
    1.03
     totals
    0.87
     tallied
    0.83
    ming
    0.76
    ries
    0.73
    enhagen
    0.71
    oire
    0.71
    sheets
    0.70
    sheet
    0.70
    Activations Density 0.010%

    No Known Activations