© 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. 1103
    Prev
    Next
    INDEX
    Explanations

    technical terms and descriptions related to coding, gaming, and digital activities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to gaming mechanics and rewards

    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
    esters
    -0.76
    yet
    -0.63
    icult
    -0.61
    ©¶æ
    -0.58
    ropolitan
    -0.57
    enged
    -0.57
    overty
    -0.56
    atican
    -0.55
     fears
    -0.55
    ]"
    -0.55
    POSITIVE LOGITS
     whenever
    1.19
     depending
    1.15
     proportional
    1.06
     automatically
    1.00
     periodically
    0.99
     corresponding
    0.93
     indicating
    0.92
     whichever
    0.91
     instantly
    0.91
     respectively
    0.88
    Activations Density 0.371%

    No Known Activations