© 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. 2-RES-JB
    11. 11096
    Prev
    Next
    INDEX
    Explanations

    words related to positions or roles within a political shadow cabinet

    oai_token-act-pair · gpt-3.5-turbo

    references to "shadow" in various contexts, indicating themes related to lack of visibility or influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    urses
    -0.90
    tics
    -0.83
    sburgh
    -0.79
    atically
    -0.78
    anchester
    -0.76
    agonists
    -0.74
    olics
    -0.74
    entric
    -0.73
    otide
    -0.73
    apsed
    -0.73
    POSITIVE LOGITS
    moon
    1.05
     shadow
    1.05
     Shadow
    1.04
    shadow
    0.90
    Shadow
    0.88
     Shadows
    0.87
    loo
    0.84
    hawk
    0.80
     shadows
    0.77
    boxing
    0.71
    Activations Density 0.008%

    No Known Activations