© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 9870
    Prev
    Next
    INDEX
    Explanations

    text related to social and political issues or discussions

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and phrases related to social and political issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etts
    -0.78
     Sparks
    -0.77
    ouses
    -0.75
     Wins
    -0.70
    uses
    -0.70
    153
    -0.67
    lets
    -0.67
    ffect
    -0.66
     Bung
    -0.65
    quit
    -0.64
    POSITIVE LOGITS
     economic
    1.28
     familial
    1.12
     ecological
    1.11
     linguistic
    1.11
     cultural
    1.10
     political
    1.09
     socioeconomic
    1.08
    economic
    1.06
     demographic
    1.05
     racial
    1.05
    Activations Density 0.044%

    No Known Activations