© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 11961
    Prev
    Next
    INDEX
    Explanations

    mentions or occurrences of governmental or official actions and bodies

    oai_token-act-pair · gpt-3.5-turbo

    references to official committees or commissions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Klu
    -0.90
     Tibetan
    -0.68
     Dharma
    -0.65
     Quartz
    -0.64
    vae
    -0.62
    upt
    -0.62
    VK
    -0.62
     Bieber
    -0.61
    yu
    -0.61
    rella
    -0.61
    POSITIVE LOGITS
     commissions
    1.20
     commission
    1.05
     commissioners
    1.03
    issions
    0.81
     inquiry
    0.75
    ittee
    0.75
    eers
    0.74
    Commission
    0.73
    ing
    0.72
     Commissioners
    0.72
    Activations Density 0.009%

    No Known Activations