© 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. 0-RES-JB
    11. 15440
    Prev
    Next
    INDEX
    Explanations

    adjectives related to criticism and negativity

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases that indicate flaws or faults in methods, systems, or arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Emin
    -0.71
    rons
    -0.68
    ants
    -0.65
     Immediately
    -0.65
    enter
    -0.64
    ant
    -0.64
     Torrent
    -0.63
    sburg
    -0.62
     Colon
    -0.62
    enth
    -0.60
    POSITIVE LOGITS
     flawed
    3.50
     faulty
    2.22
     defective
    1.80
     misguided
    1.71
     tainted
    1.65
     flaws
    1.59
     dysfunctional
    1.56
     outdated
    1.54
     discredited
    1.50
     unreliable
    1.50
    Activations Density 0.026%

    No Known Activations