© 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. 6-RES-JB
    11. 18917
    Prev
    Next
    INDEX
    Explanations

    words related to negative economic outcomes or political destabilization

    oai_token-act-pair · gpt-3.5-turbo

    terms related to economic instability and crises

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     establishments
    -0.84
    azines
    -0.83
    iaries
    -0.82
     Occupations
    -0.80
    itudes
    -0.78
     newsletters
    -0.75
     Cups
    -0.72
     exhibits
    -0.71
    eworks
    -0.70
     caf
    -0.70
    POSITIVE LOGITS
    able
    0.82
    earance
    0.81
    urrence
    0.81
    ittal
    0.81
     akin
    0.80
    atical
    0.80
     standpoint
    0.78
    aration
    0.77
    inition
    0.76
     thereof
    0.74
    Activations Density 0.270%

    No Known Activations