© 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. 7582
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports tournaments or competitions

    oai_token-act-pair · gpt-3.5-turbo

    references to competition and rankings, particularly in sports contexts

    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
    pora
    -0.73
     veins
    -0.67
    otom
    -0.65
    othal
    -0.64
    clerosis
    -0.64
    utory
    -0.63
    actionDate
    -0.61
    ategory
    -0.60
    ounty
    -0.60
    ĸļ
    -0.59
    POSITIVE LOGITS
     Worst
    0.81
     Practices
    0.72
     outcomes
    0.68
     brightest
    0.66
     EVER
    0.65
     Possible
    0.65
     hindsight
    0.63
     luck
    0.63
    luck
    0.62
     contrace
    0.62
    Activations Density 0.182%

    No Known Activations