© 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. 10-RES-JB
    11. 18681
    Prev
    Next
    INDEX
    Explanations

    instances where people are expressing their opinions or making evaluations

    oai_token-act-pair · gpt-3.5-turbo

    words related to evaluating or considering options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kart
    -0.72
    algia
    -0.72
    ãĥĨãĤ£
    -0.71
    nered
    -0.70
    etheless
    -0.69
    later
    -0.67
    anie
    -0.67
    chief
    -0.66
    ITIES
    -0.65
     Parables
    -0.65
    POSITIVE LOGITS
     weigh
    1.16
     weighing
    0.97
     weighed
    0.93
     weights
    0.88
     heaviest
    0.84
     pros
    0.82
     weighs
    0.80
     heavily
    0.80
     heavier
    0.78
    iless
    0.77
    Activations Density 0.029%

    No Known Activations