© 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. 1939
    Prev
    Next
    INDEX
    Explanations

    instances where something is not completed or successful

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the action of creating or achieving something

    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
    heter
    -0.69
    rone
    -0.66
    æ©Ł
    -0.66
    accompanied
    -0.64
    bour
    -0.62
     withd
    -0.61
    cius
    -0.60
     Niet
    -0.59
    pun
    -0.58
    rogen
    -0.57
    POSITIVE LOGITS
     landfall
    1.12
     headlines
    0.96
     strides
    0.94
     sense
    0.94
     waves
    0.87
    hift
    0.85
     progress
    0.84
     ends
    0.80
    sense
    0.80
     it
    0.79
    Activations Density 0.078%

    No Known Activations