© 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. 10-RES-JB
    11. 17262
    Prev
    Next
    INDEX
    Explanations

    financial and business terms

    oai_token-act-pair · gpt-3.5-turbo

    key phrases related to media partnerships and access to content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lately
    -1.05
    paren
    -0.93
    Yesterday
    -0.83
     desper
    -0.73
     Wrong
    -0.72
     Yesterday
    -0.71
     wrong
    -0.71
     scares
    -0.70
     hyster
    -0.70
     dreaded
    -0.69
    POSITIVE LOGITS
     2024
    0.85
     2021
    0.85
     jointly
    0.85
     unspecified
    0.81
     subsidiaries
    0.80
     alongside
    0.79
     2020
    0.77
     overseen
    0.77
     whichever
    0.77
     2025
    0.76
    Activations Density 0.522%

    No Known Activations