© 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. 4-RES-JB
    11. 3739
    Prev
    Next
    INDEX
    Explanations

    references to economic recessions

    oai_token-act-pair · gpt-3.5-turbo

    references to economic recessions

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

    No Comments

    Negative Logits
    tein
    -0.84
    Male
    -0.73
    VICE
    -0.73
    missions
    -0.72
    WAYS
    -0.72
    CHO
    -0.69
    Points
    -0.69
    */(
    -0.69
    metics
    -0.68
    rol
    -0.66
    POSITIVE LOGITS
     recession
    1.07
     Recession
    1.05
     downturn
    1.04
     meltdown
    0.81
     slump
    0.77
     plag
    0.75
     apocalypse
    0.75
     depression
    0.73
     Depression
    0.72
     forecast
    0.71
    Activations Density 0.012%

    No Known Activations