© 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. 9-RES-JB
    11. 3578
    Prev
    Next
    INDEX
    Explanations

    information related to economic and financial topics

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to significant legal and financial events or decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     realise
    -0.96
     behaviours
    -0.84
     whilst
    -0.80
     Whilst
    -0.79
     realised
    -0.79
     analyse
    -0.77
    isations
    -0.77
     endeavour
    -0.75
     learnt
    -0.74
     alot
    -0.74
    POSITIVE LOGITS
     staffers
    0.77
    irteen
    0.73
     Sawyer
    0.72
     Bryce
    0.72
     prosecutors
    0.72
     lawmakers
    0.71
     JPMorgan
    0.70
     officials
    0.68
     Amtrak
    0.68
     Maryland
    0.68
    Activations Density 0.847%

    No Known Activations