© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 10240
    Prev
    Next
    INDEX
    Explanations

    words related to different types of fries

    oai_token-act-pair · gpt-3.5-turbo

    words related to various types of "ries" or "dried" items, specifically focusing on categories or classifications

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

    No Comments

    Negative Logits
    ilogy
    -0.78
    agonists
    -0.78
    CVE
    -0.75
    anooga
    -0.75
    ancial
    -0.75
    earable
    -0.74
    insula
    -0.72
    Reviewer
    -0.71
    irlf
    -0.70
    etheless
    -0.70
    POSITIVE LOGITS
    ries
    1.00
    lander
    0.87
    stal
    0.85
    stall
    0.81
    EF
    0.80
    gaard
    0.78
    cks
    0.77
    stals
    0.74
    vier
    0.74
    ried
    0.72
    Activations Density 0.014%

    No Known Activations