© 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. 6-RES-JB
    11. 7637
    Prev
    Next
    INDEX
    Explanations

    sports-related terms and actions

    oai_token-act-pair · gpt-3.5-turbo

    entities and specific terms related to team sports and organizational structures

    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
    姫
    -0.84
    urrencies
    -0.74
     Scouts
    -0.70
     Videos
    -0.68
     channels
    -0.67
    imil
    -0.66
     magnets
    -0.66
    tics
    -0.65
    doms
    -0.65
     clauses
    -0.64
    POSITIVE LOGITS
     similar
    0.79
    elist
    0.75
    robe
    0.74
     titled
    0.73
     named
    0.73
     akin
    0.73
     consisting
    0.71
    cko
    0.70
     standpoint
    0.70
     entitled
    0.68
    Activations Density 0.500%

    No Known Activations