© 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. 11-RES-JB
    11. 6629
    Prev
    Next
    INDEX
    Explanations

    prepositions and conjunctions as well as terms relating to using something for a specific purpose

    oai_token-act-pair · gpt-3.5-turbo

    instructions or references related to the usage of software or tools in documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hoe
    -0.70
    ãĤ©
    -0.68
    hya
    -0.66
    ixty
    -0.66
    ãĥ´ãĤ¡
    -0.66
    erd
    -0.64
    oxin
    -0.62
    itled
    -0.62
    urable
    -0.62
    tein
    -0.61
    POSITIVE LOGITS
     other
    1.23
     others
    1.09
     Others
    0.96
     another
    0.94
     existing
    0.94
     Other
    0.90
     your
    0.89
     elsewhere
    0.89
     OTHER
    0.87
     any
    0.86
    Activations Density 0.335%

    No Known Activations