Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 10499
    Prev
    Next
    INDEX
    Explanations

    adjectives and nouns related to different perspectives - including financial, moral, theoretical, political, cultural, legal, behavioral, institutional, geopolitical, and diplomatic

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various aspects of political, economic, and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nces
    -0.96
    lees
    -0.93
    ages
    -0.91
     Rooms
    -0.90
    casts
    -0.87
    keys
    -0.87
    esters
    -0.86
    votes
    -0.85
    bats
    -0.84
    sites
    -0.84
    POSITIVE LOGITS
     standpoint
    1.36
     phenomenon
    1.17
     nightmare
    1.15
     perspective
    1.12
     impossibility
    1.11
     dilemma
    1.09
     basis
    1.05
     headache
    1.04
     imperative
    1.03
     problem
    1.01
    Activations Density 0.238%

    No Known Activations