© 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. 10-RES-JB
    11. 24479
    Prev
    Next
    INDEX
    Explanations

    critiques of various societal and political issues

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to societal and political decay or crises

    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
    hex
    -0.70
    fixes
    -0.68
    display
    -0.67
    article
    -0.67
    zilla
    -0.66
     Eater
    -0.66
    deck
    -0.65
    lag
    -0.65
    rants
    -0.65
    iannopoulos
    -0.64
    POSITIVE LOGITS
     credibility
    1.47
     legitimacy
    1.20
     confidence
    1.20
     trust
    1.18
     cherished
    1.18
     sanity
    1.18
     morale
    1.13
     cohesion
    1.12
     integrity
    1.12
     democracy
    1.11
    Activations Density 0.524%

    No Known Activations