© 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
    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. 1102
    Prev
    Next
    INDEX
    Explanations

    descriptions related to digital collaboration and interactive platforms

    oai_token-act-pair · gpt-3.5-turbo

    elements related to interactive and collaborative media

    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
     Bermuda
    -0.66
    ricane
    -0.65
     Renew
    -0.64
     Bav
    -0.64
     Bung
    -0.64
     Brunswick
    -0.64
     Newport
    -0.63
     scourge
    -0.63
     Nug
    -0.63
     Pennsylvania
    -0.62
    POSITIVE LOGITS
     narration
    1.27
     interactive
    1.19
     narr
    1.16
     dialog
    1.16
     viewer
    1.15
     immersive
    1.14
     subconscious
    1.14
     interact
    1.12
     listener
    1.11
     audience
    1.09
    Activations Density 0.775%

    No Known Activations