© 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. 11-RES-JB
    11. 4927
    Prev
    Next
    INDEX
    Explanations

    government and organization-related entities or activities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to governmental or organizational entities

    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
    rovers
    -0.71
    geries
    -0.65
     obscurity
    -0.65
    entious
    -0.63
    Appearances
    -0.62
     die
    -0.61
     conflic
    -0.61
    escape
    -0.61
    Ò
    -0.61
    Breaking
    -0.60
    POSITIVE LOGITS
     intends
    1.61
     expects
    1.54
     plans
    1.49
     hopes
    1.48
     anticip
    1.37
     aims
    1.28
     wants
    1.23
     hoped
    1.20
     will
    1.18
     planned
    1.17
    Activations Density 0.294%

    No Known Activations