© 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. 6-RES-JB
    11. 3118
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to negative feelings, opinions, or perceptions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to negative economic perceptions and their impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    natureconservancy
    -0.73
    WARN
    -0.69
    EStream
    -0.68
    ulhu
    -0.66
     intricate
    -0.65
    ptin
    -0.65
    Effective
    -0.65
    SEA
    -0.65
    ĸļ
    -0.64
     refin
    -0.64
    POSITIVE LOGITS
     outweigh
    0.87
    agonist
    0.85
     outwe
    0.76
     Syndrome
    0.75
    iation
    0.73
    rencies
    0.68
     cov
    0.66
    achev
    0.66
    stadt
    0.66
     syndrome
    0.65
    Activations Density 0.188%

    No Known Activations