© 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. 23807
    Prev
    Next
    INDEX
    Explanations

    phrases related to nuclear disarmament

    oai_token-act-pair · gpt-3.5-turbo

    terms related to nuclear disarmament

    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
    alph
    -0.82
     Preferred
    -0.80
    ungle
    -0.77
     Dough
    -0.76
     Cum
    -0.74
     Hive
    -0.70
    Bee
    -0.68
    JP
    -0.67
    Dub
    -0.67
     Reaper
    -0.67
    POSITIVE LOGITS
     disarm
    1.36
    ament
    1.21
    aments
    0.96
    ingly
    0.94
    atures
    0.94
    achev
    0.86
    olesterol
    0.85
    atories
    0.82
     treaty
    0.81
     tender
    0.81
    Activations Density 0.015%

    No Known Activations