© 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. 452
    Prev
    Next
    INDEX
    Explanations

    URL shortening links

    oai_token-act-pair · gpt-3.5-turbo

    website URLs and their formats

    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
    ADA
    -0.63
     civilisation
    -0.60
     Genie
    -0.59
     citizenship
    -0.58
     hospitality
    -0.57
    phia
    -0.56
     Dome
    -0.56
     srfAttach
    -0.55
     Peg
    -0.55
     Zac
    -0.55
    POSITIVE LOGITS
    ly
    1.11
    dyl
    0.83
    assetsadobe
    0.81
    pmwiki
    0.80
    php
    0.80
    json
    0.79
    pload
    0.78
    fb
    0.76
    mg
    0.75
    ssl
    0.75
    Activations Density 0.039%

    No Known Activations