© 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. 3-RES-JB
    11. 10633
    Prev
    Next
    INDEX
    Explanations

    words related to economics and financial matters

    oai_token-act-pair · gpt-3.5-turbo

    references to economic arguments and discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    netflix
    -0.85
    umbn
    -0.78
    tower
    -0.78
     Kens
    -0.76
    etts
    -0.73
     Wem
    -0.73
    enic
    -0.73
    KEN
    -0.73
     Bans
    -0.72
    eeper
    -0.71
    POSITIVE LOGITS
     downturn
    1.11
     meltdown
    0.90
     inequality
    0.90
     prosperity
    0.86
     exploitation
    0.85
     illiter
    0.85
     hardship
    0.84
     upheaval
    0.84
     sanctions
    0.83
     instability
    0.83
    Activations Density 0.024%

    No Known Activations