Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 6-RES-JB
    6. 20908
    Prev
    Next
    INDEX
    Explanations

    This neuron is looking for sentences related to sports trades and player contracts

    oai_token-act-pair · gpt-3.5-turbo

    details related to contractual agreements and trade situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Feminist
    -0.86
     pixels
    -0.76
     cinema
    -0.74
     UNESCO
    -0.74
    rika
    -0.74
     liter
    -0.70
     feminist
    -0.70
     humour
    -0.69
     Lanc
    -0.68
     behavi
    -0.68
    POSITIVE LOGITS
     waivers
    1.13
     undrafted
    1.12
     offseason
    1.10
    signed
    0.99
    Contract
    0.98
     signings
    0.95
     roster
    0.92
     waive
    0.92
    abilia
    0.92
     salary
    0.91
    Activations Density 0.692%

    No Known Activations