© 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
    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. 17130
    Prev
    Next
    INDEX
    Explanations

    keywords related to dystopian settings or themes

    oai_token-act-pair · gpt-3.5-turbo

    themes related to dystopian and futuristic narratives

    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
    alties
    -0.91
    Bone
    -0.78
    CV
    -0.74
    bro
    -0.74
    DN
    -0.72
    uana
    -0.72
    gs
    -0.72
    Reviewer
    -0.71
    eva
    -0.70
    oyal
    -0.70
    POSITIVE LOGITS
     dystop
    1.00
     dystopian
    0.98
     scenarios
    0.98
     futuristic
    0.96
    ocalyptic
    0.90
    ocalypse
    0.86
     scenario
    0.85
     Apocalypse
    0.84
     visions
    0.84
     Reloaded
    0.81
    Activations Density 0.029%

    No Known Activations