© 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. 2-RES-JB
    11. 5293
    Prev
    Next
    INDEX
    Explanations

    negative aspects or drawbacks in various scenarios

    oai_token-act-pair · gpt-3.5-turbo

    terms related to negative aspects or drawbacks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ingham
    -0.82
    tein
    -0.70
    chin
    -0.70
    ondon
    -0.69
    mberg
    -0.69
    atorial
    -0.69
    onement
    -0.67
    iverpool
    -0.65
    itar
    -0.64
    pelled
    -0.64
    POSITIVE LOGITS
     downside
    1.27
     drawback
    1.02
     disadvantages
    0.85
     drawbacks
    0.84
     aversion
    0.83
     undermin
    0.83
     surprises
    0.80
     deterrent
    0.78
     spoilers
    0.76
     pitfalls
    0.75
    Activations Density 0.019%

    No Known Activations