© 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. 6523
    Prev
    Next
    INDEX
    Explanations

    mentions of companies and organizations, especially when they are named in full

    oai_token-act-pair · gpt-3.5-turbo

    corporate names and references to business entities

    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
     poems
    -0.74
     coma
    -0.73
     poem
    -0.70
     fatigue
    -0.67
     frustration
    -0.66
     flashbacks
    -0.65
     nausea
    -0.65
     impat
    -0.65
     hunger
    -0.64
     selfies
    -0.64
    POSITIVE LOGITS
     headquartered
    1.06
     sponsoring
    0.96
     subsidiaries
    0.94
    operated
    0.89
     specializing
    0.88
     staffed
    0.87
     subcontract
    0.83
     supplying
    0.82
     operated
    0.81
     subsidiary
    0.81
    Activations Density 1.434%

    No Known Activations