© 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. 11-RES-JB
    11. 21309
    Prev
    Next
    INDEX
    Explanations

    instances of phrases specifically related to the name "Hearts of Iron IV"

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "of the."

    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
    fully
    -0.76
     stunts
    -0.74
    OTOS
    -0.70
    LET
    -0.70
    Ô
    -0.69
    isms
    -0.68
    âĶģ
    -0.67
    cycles
    -0.65
    nels
    -0.65
    legal
    -0.64
    POSITIVE LOGITS
    nir
    0.82
     Fury
    0.82
     Darkness
    0.77
    rimination
    0.76
     Wheat
    0.75
    thora
    0.73
     Grass
    0.73
     Autumn
    0.73
     Destruction
    0.72
     Vengeance
    0.71
    Activations Density 0.067%

    No Known Activations