© 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. 17147
    Prev
    Next
    INDEX
    Explanations

    words related to the brand "Lomography" or words with the substring "om" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "om" or related variations

    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
    LIST
    -0.69
    ++++++++++++++++
    -0.67
     Actual
    -0.66
     Forsaken
    -0.63
     separatist
    -0.62
     Wad
    -0.60
     nexus
    -0.60
     Border
    -0.59
     Brees
    -0.59
     Kindle
    -0.58
    POSITIVE LOGITS
    orrow
    1.11
    puter
    1.08
    obile
    1.07
    useum
    1.05
    otive
    1.02
    atoes
    1.01
    pson
    0.97
    edia
    0.96
    obiles
    0.95
    ikawa
    0.95
    Activations Density 0.013%

    No Known Activations