© 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. 3-RES-JB
    11. 1888
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Sw" followed by a single character and then a number

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Sw" followed by various endings, indicating a focus on specific entities or brands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OPLE
    -0.77
    EStream
    -0.72
    BILITY
    -0.70
    cised
    -0.70
    66666666
    -0.67
     theater
    -0.66
     preferential
    -0.66
    vre
    -0.66
     partial
    -0.65
    代
    -0.65
    POSITIVE LOGITS
    immer
    1.14
    inton
    1.13
    imming
    1.13
    addle
    1.11
    ifty
    1.11
    artz
    1.10
    indle
    1.07
    ollen
    1.06
    allow
    1.05
    inging
    1.04
    Activations Density 0.007%

    No Known Activations