© 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. 8-RES-JB
    11. 7918
    Prev
    Next
    INDEX
    Explanations

    words related to intensity or strength

    oai_token-act-pair · gpt-3.5-turbo

    words related to independence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MQ
    -0.72
    veyard
    -0.68
    Ĥİ
    -0.65
    --+
    -0.65
    Gate
    -0.64
    BY
    -0.62
    calling
    -0.61
    culosis
    -0.61
    sonian
    -0.61
     Lumpur
    -0.60
    POSITIVE LOGITS
    ented
    1.07
    etermin
    1.01
    oled
    0.98
    irection
    0.89
    ents
    0.89
    iour
    0.85
    etr
    0.84
    ignant
    0.83
    inged
    0.83
    rawn
    0.83
    Activations Density 0.031%

    No Known Activations