© 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. 7784
    Prev
    Next
    INDEX
    Explanations

    phrases related to construction and development

    oai_token-act-pair · gpt-3.5-turbo

    infinitive verbs, particularly those conveying intent or purpose

    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
     misses
    -0.74
    announced
    -0.67
     Decision
    -0.63
     Changes
    -0.63
    Got
    -0.61
     VIDEOS
    -0.60
    Returns
    -0.60
     Written
    -0.60
     Perspective
    -0.59
    done
    -0.58
    POSITIVE LOGITS
     accommodate
    1.36
     withstand
    1.27
     accompany
    1.24
     facilitate
    1.18
     cope
    1.18
     serve
    1.18
     emulate
    1.15
     handle
    1.14
     compete
    1.14
     replace
    1.13
    Activations Density 0.163%

    No Known Activations