© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 15406
    Prev
    Next
    INDEX
    Explanations

    mentions of trade-related actions or discussions, such as trading players or seeking trade scenarios

    oai_token-act-pair · gpt-3.5-turbo

    terms related to player trades in sports contexts

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

    No Comments

    Negative Logits
    alach
    -0.85
    isan
    -0.82
    osate
    -0.78
    icka
    -0.74
    idem
    -0.72
     Continental
    -0.72
    atts
    -0.69
    ire
    -0.68
     WARN
    -0.67
    Gi
    -0.66
    POSITIVE LOGITS
     waivers
    0.91
     deadline
    0.81
     acquisitions
    0.76
     swaps
    0.74
     bait
    0.73
     arms
    0.73
    able
    0.73
    offs
    0.71
     waiver
    0.71
     kicker
    0.71
    Activations Density 0.033%

    No Known Activations