© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 4031
    Prev
    Next
    INDEX
    Explanations

    numbers indicating player positions or scores in sports contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "to" indicating actions or goals in a sports context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     traveller
    -0.65
     postings
    -0.65
     parameters
    -0.65
     overcl
    -0.64
     behaviors
    -0.63
     conversations
    -0.62
     messages
    -0.62
     interactions
    -0.61
     perce
    -0.61
     behaviours
    -0.60
    POSITIVE LOGITS
     clinch
    1.01
     earn
    0.97
     propel
    0.94
     satisfy
    0.89
     topple
    0.88
     appease
    0.86
     celebrate
    0.86
     begin
    0.86
     signify
    0.86
     commemorate
    0.84
    Activations Density 0.160%

    No Known Activations