© 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. 10-RES-JB
    11. 17372
    Prev
    Next
    INDEX
    Explanations

    phrases related to positive performance or achievement in sports

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "and" along with related phrases indicating multiple actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    actionDate
    -0.86
    ictionary
    -0.80
    emn
    -0.79
    minist
    -0.76
    scribe
    -0.75
    payer
    -0.74
    uct
    -0.73
    ities
    -0.73
    insula
    -0.72
    Enlarge
    -0.71
    POSITIVE LOGITS
     secondly
    0.93
     luckily
    0.93
     consequently
    0.90
     thus
    0.89
     showed
    0.87
     thankfully
    0.86
     deserved
    0.86
     scored
    0.85
     hopefully
    0.85
     ensured
    0.85
    Activations Density 0.184%

    No Known Activations