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. 11-RES-JB
    6. 22678
    Prev
    Next
    INDEX
    Explanations

    phrases related to organizations, positions, and policies

    oai_token-act-pair · gpt-3.5-turbo

    references to authoritative sources and organizations

    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
    selection
    -0.76
    EXT
    -0.71
     ensued
    -0.70
    /**
    -0.69
    dyl
    -0.67
    iques
    -0.66
    utations
    -0.66
     solves
    -0.65
     proves
    -0.65
    pai
    -0.65
    POSITIVE LOGITS
     nonpartisan
    1.24
     nonprofit
    1.22
     Center
    1.18
     Partnership
    1.15
     Association
    1.06
     advocacy
    1.04
     Coalition
    1.03
     Federation
    1.02
     Institute
    1.02
     Campaign
    1.01
    Activations Density 0.138%

    No Known Activations