© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 8-RES-JB
    11. 19346
    Prev
    Next
    INDEX
    Explanations

    phrases related to contrasting situations

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "ups and downs" and related conjunctions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.96
    hower
    -0.87
    advertisement
    -0.82
    arette
    -0.76
    arro
    -0.76
    alert
    -0.69
    ONSORED
    -0.67
    tesy
    -0.66
    nant
    -0.65
    GREEN
    -0.64
    POSITIVE LOGITS
     pains
    0.88
     valleys
    0.87
     souls
    0.82
     bruises
    0.81
     disabilities
    0.80
     oranges
    0.79
     bolts
    0.79
    uries
    0.78
     heals
    0.77
     crafts
    0.76
    Activations Density 0.267%

    No Known Activations