© 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. 4-RES-JB
    11. 24470
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "hat"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "hat"

    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
     glutamate
    -0.68
    hyde
    -0.67
    á½
    -0.61
     Vaugh
    -0.61
    agine
    -0.60
     tremend
    -0.58
    hower
    -0.58
     medic
    -0.58
    idge
    -0.58
     Gly
    -0.58
    POSITIVE LOGITS
    chet
    1.18
    chery
    1.09
    dar
    0.93
    ullah
    0.92
    ia
    0.90
    ches
    0.85
    cher
    0.84
    ril
    0.84
    red
    0.82
    ched
    0.79
    Activations Density 0.006%

    No Known Activations