© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 4218
    Prev
    Next
    INDEX
    Explanations

    phrases related to socio-political and economic conditions

    oai_token-act-pair · gpt-3.5-turbo
    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
    BILL
    -0.74
    !/
    -0.72
    EX
    -0.71
     WATCHED
    -0.71
    staking
    -0.70
    esc
    -0.69
    ANE
    -0.68
    daq
    -0.68
    Ly
    -0.67
    AAA
    -0.67
    POSITIVE LOGITS
     nations
    1.04
     countries
    1.01
     societies
    0.96
     Europe
    0.89
     contemporary
    0.88
     rural
    0.87
     society
    0.86
     states
    0.85
     industrialized
    0.84
     democracies
    0.82
    Activations Density 0.327%

    No Known Activations