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. 1947
    Prev
    Next
    INDEX
    Explanations

    words related to sports defenders

    oai_token-act-pair · gpt-3.5-turbo

    references to defenders in sports contexts

    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
    ibal
    -0.78
    isan
    -0.77
    oros
    -0.74
    orie
    -0.71
    lie
    -0.70
    cow
    -0.69
    ombat
    -0.66
    yss
    -0.66
     Fishing
    -0.66
    Lear
    -0.65
    POSITIVE LOGITS
    ngth
    0.89
     defender
    0.87
     defenders
    0.85
    bane
    0.76
     Allan
    0.69
     defending
    0.69
    iants
    0.69
     outfielder
    0.68
     corps
    0.67
     protecting
    0.67
    Activations Density 0.022%

    No Known Activations