© 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. 3-RES-JB
    11. 5959
    Prev
    Next
    INDEX
    Explanations

    words related to negativity or adverse conditions

    oai_token-act-pair · gpt-3.5-turbo

    discussions about negativity and its impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ITNESS
    -0.92
    pread
    -0.83
    akings
    -0.82
    DOM
    -0.82
    dropping
    -0.81
    conservancy
    -0.81
    hower
    -0.80
    adr
    -0.79
    olds
    -0.78
    ĸļ
    -0.78
    POSITIVE LOGITS
     reinforcement
    1.04
     Negative
    1.01
     negative
    0.95
     spiral
    0.93
     stigma
    0.89
     feedback
    0.89
     vib
    0.88
     publicity
    0.86
     karma
    0.85
     impact
    0.83
    Activations Density 0.017%

    No Known Activations