© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 13932
    Prev
    Next
    INDEX
    Explanations

    terms related to political and economic discussions, including words related to policies, taxation, and trading

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to patriotism and socio-political issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FactoryReloaded
    -0.59
    Reviewer
    -0.59
    ]."
    -0.58
    DCS
    -0.56
    ?".
    -0.54
    bart
    -0.54
    ////////
    -0.50
    )).
    -0.50
    ").
    -0.50
    CONCLUS
    -0.50
    POSITIVE LOGITS
     meanwhile
    0.51
     depleted
    0.51
     replaced
    0.50
     likewise
    0.48
     Prelude
    0.45
     Chou
    0.44
     Hait
    0.44
     Shutterstock
    0.44
     Thu
    0.43
     reminiscent
    0.42
    Activations Density 1.954%

    No Known Activations