© 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. 7-RES-JB
    6. 8954
    Prev
    Next
    INDEX
    Explanations

    technical terms and jargon, such as specific industry-related phrases and concepts

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to commonly discussed subjects or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BuyableInstoreAndOnline
    -0.73
     Harmony
    -0.69
    Record
    -0.68
    Rated
    -0.67
    sburg
    -0.66
    Whe
    -0.66
    Hit
    -0.64
     Hitman
    -0.64
    aretz
    -0.60
    DR
    -0.60
    POSITIVE LOGITS
     commonly
    0.92
     acronym
    0.89
     coined
    0.88
     simplest
    0.85
     basically
    0.85
     fancy
    0.84
    ptoms
    0.84
    common
    0.83
     originated
    0.82
     abbre
    0.82
    Activations Density 0.505%

    No Known Activations