© 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. 1-RES-JB
    11. 14259
    Prev
    Next
    INDEX
    Explanations

    keywords related to software or product releases

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "releases" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ń·
    -0.69
     Antar
    -0.67
     Pratt
    -0.67
     Neh
    -0.66
    notations
    -0.66
     Et
    -0.66
     Corinth
    -0.66
     Must
    -0.66
     Zamb
    -0.65
    immer
    -0.65
    POSITIVE LOGITS
     releases
    1.24
     RELEASE
    1.22
    release
    1.21
     release
    1.18
    Release
    1.10
     releasing
    1.07
     Release
    1.06
    released
    1.01
    LEASE
    1.00
     RELE
    0.99
    Activations Density 0.028%

    No Known Activations