© 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. 0-RES-JB
    11. 8012
    Prev
    Next
    INDEX
    Explanations

    words related to politics and news

    oai_token-act-pair · gpt-3.5-turbo

    words and terms associated with politics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    airs
    -0.84
    Sleep
    -0.74
     Sew
    -0.74
     shave
    -0.72
     Saras
    -0.71
     neigh
    -0.70
    air
    -0.70
     Pine
    -0.70
     Sunder
    -0.68
    ago
    -0.67
    POSITIVE LOGITS
    polit
    2.44
     ND
    1.37
     intens
    1.31
     gam
    1.22
     grat
    1.21
    cod
    1.11
     quant
    1.00
    Cod
    0.98
     cod
    0.97
    Polit
    0.97
    Activations Density 0.066%

    No Known Activations