© 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. 9030
    Prev
    Next
    INDEX
    Explanations

    studies or reports containing data or analysis

    oai_token-act-pair · gpt-3.5-turbo

    references to studies and analyses related to data and reports

    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
    dial
    -0.76
    GBT
    -0.71
    twitch
    -0.68
     antagonists
    -0.67
     orally
    -0.66
     epit
    -0.66
     funer
    -0.66
     receptor
    -0.65
    vo
    -0.65
     transpl
    -0.64
    POSITIVE LOGITS
     forecasts
    1.07
     projections
    1.00
     forecast
    0.98
     estimates
    0.87
     analyst
    0.85
     estimate
    0.85
    ashington
    0.80
    aez
    0.79
    alyst
    0.78
     estimating
    0.77
    Activations Density 0.241%

    No Known Activations