© 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. 6-RES-JB
    6. 1596
    Prev
    Next
    INDEX
    Explanations

    food-related items such as items of food or ingredients

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate alternatives or choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ires
    -0.79
    ocrats
    -0.71
    OTAL
    -0.66
    enko
    -0.63
    qqa
    -0.63
    ETS
    -0.62
    igned
    -0.61
    masters
    -0.60
    IGHTS
    -0.60
    yet
    -0.59
    POSITIVE LOGITS
    acle
    1.27
    ifice
    1.21
    chid
    1.21
    chard
    1.17
    acles
    1.13
    Else
    1.11
    nam
    1.11
    lando
    1.04
    whatever
    1.02
    acular
    1.00
    Activations Density 0.162%

    No Known Activations