© 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. 3-RES-JB
    11. 1845
    Prev
    Next
    INDEX
    Explanations

    mentions of customizations or custom-made items in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to custom-made or tailored products and features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ï¸
    -0.90
    OPE
    -0.77
     Kinn
    -0.76
     Mub
    -0.76
     Lauder
    -0.74
     Mubarak
    -0.70
    oof
    -0.70
     CrossRef
    -0.69
     Crosby
    -0.67
    Gary
    -0.66
    POSITIVE LOGITS
    isable
    1.42
    izations
    1.29
    arily
    1.23
    isations
    1.20
    ised
    1.16
    izable
    1.11
    isation
    1.06
    ization
    0.92
    izes
    0.90
    izing
    0.89
    Activations Density 0.012%

    No Known Activations