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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10-RES-JB
    11. 2931
    Prev
    Next
    INDEX
    Explanations

    political figures and election-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to political events and figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     --
    -1.14
     »
    -1.02
     âĢķ
    -0.96
     ...
    -0.95
     ---
    -0.82
     ]
    -0.77
    »
    -0.77
     âĢ¦
    -0.77
     �
    -0.75
     RCMP
    -0.74
    POSITIVE LOGITS
     (£
    0.76
     Nato
    0.72
     Suppose
    0.71
     Wales
    0.68
     Tottenham
    0.66
     Whilst
    0.65
     Wembley
    0.64
    £
    0.64
     £
    0.63
     Nobel
    0.63
    Activations Density 0.031%

    No Known Activations