© 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. 8306
    Prev
    Next
    INDEX
    Explanations

    words related to expressing dissatisfaction or criticism

    oai_token-act-pair · gpt-3.5-turbo

    instances of complaints or expressions of dissatisfaction

    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
    ãĥ¯
    -0.67
    ahime
    -0.66
    è¡
    -0.64
    arte
    -0.61
    DragonMagazine
    -0.60
    iral
    -0.60
    elta
    -0.59
    ective
    -0.58
    instance
    -0.58
     conflic
    -0.56
    POSITIVE LOGITS
     bitterly
    1.44
     loudly
    1.24
     aloud
    1.22
     about
    1.14
     endlessly
    1.05
     incess
    1.04
     passionately
    1.01
     angrily
    1.00
     vehemently
    0.99
     furiously
    0.98
    Activations Density 0.098%

    No Known Activations