© 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. 18596
    Prev
    Next
    INDEX
    Explanations

    titles or positions related to management, leadership, or expertise

    oai_token-act-pair · gpt-3.5-turbo

    titles or roles associated with professional positions

    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
    pload
    -0.84
    SPONSORED
    -0.73
    APTER
    -0.72
    inventoryQuantity
    -0.67
    ãĥ«
    -0.66
    pmwiki
    -0.66
    TIME
    -0.64
     defy
    -0.64
    Tokens
    -0.62
    Spoiler
    -0.62
    POSITIVE LOGITS
     extraord
    1.23
     Lara
    0.87
     WWF
    0.77
     Shaun
    0.76
     emer
    0.75
     Danielle
    0.75
     Emer
    0.74
     Damon
    0.73
     specializing
    0.71
     Erik
    0.71
    Activations Density 0.124%

    No Known Activations