© 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. 10-RES-JB
    11. 10135
    Prev
    Next
    INDEX
    Explanations

    alphanumeric sequences beginning with 'U' and a high activation value, most likely related to a specific context or pattern

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the abbreviation "U" followed by numbers, indicating a focus on user-related content or metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Noir
    -0.66
     fingers
    -0.66
     chained
    -0.64
     Emin
    -0.63
     ashore
    -0.59
     trustworthy
    -0.57
     blinded
    -0.57
     Cosponsors
    -0.57
    pots
    -0.56
     istg
    -0.56
    POSITIVE LOGITS
    PLIC
    1.19
    FFER
    1.17
    ISE
    1.15
    KE
    1.15
    PDATED
    1.15
    ILD
    1.13
    NA
    1.11
    BLIC
    1.11
    YA
    1.09
    BA
    1.09
    Activations Density 0.044%

    No Known Activations