© 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. 18588
    Prev
    Next
    INDEX
    Explanations

    phrases related to criticism or evaluation, especially focused on pointing out faults or shortcomings

    oai_token-act-pair · gpt-3.5-turbo

    references to advertisements

    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
     Carbuncle
    -0.70
    FUL
    -0.64
    Jr
    -0.59
     Dame
    -0.59
     Down
    -0.58
     Strait
    -0.57
     specially
    -0.57
     Cake
    -0.56
     Sturgeon
    -0.56
     Pik
    -0.56
    POSITIVE LOGITS
    rift
    1.35
     hoc
    1.32
    idas
    1.28
    roit
    1.26
    ieu
    1.25
    hesion
    1.25
    elaide
    1.18
    missible
    1.17
    oration
    1.15
    verbs
    1.14
    Activations Density 0.015%

    No Known Activations