© 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. 15410
    Prev
    Next
    INDEX
    Explanations

    mentions of geographic locations or historical events

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "Great" indicating significant events or conditions

    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
    ograp
    -0.84
    qqa
    -0.77
    ffic
    -0.70
    clips
    -0.67
     quo
    -0.66
    PD
    -0.66
    PN
    -0.65
    ople
    -0.65
    Reloaded
    -0.64
    TeX
    -0.64
    POSITIVE LOGITS
     Lakes
    1.00
     Recession
    0.96
     Depression
    0.90
     Britain
    0.88
     Plains
    0.88
    sword
    0.86
     Barrier
    0.86
    batch
    0.85
    ness
    0.84
     Divide
    0.81
    Activations Density 0.023%

    No Known Activations