© 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. 22290
    Prev
    Next
    INDEX
    Explanations

    words related to news or updates

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "WATCH" and related phrases, indicating a focus on video or media content

    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
    gers
    -0.78
    stood
    -0.76
    lee
    -0.75
    este
    -0.74
    arist
    -0.74
    ad
    -0.74
    gy
    -0.71
    athe
    -0.70
    ator
    -0.70
    esse
    -0.70
    POSITIVE LOGITS
    INGTON
    1.26
    BOOK
    1.24
    MORE
    1.22
    HEAD
    1.19
    ISM
    1.16
     PHOTO
    1.15
    DOWN
    1.14
    OGR
    1.12
     REPORT
    1.11
    ATURE
    1.10
    Activations Density 0.039%

    No Known Activations