© 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. 4-RES-JB
    11. 13575
    Prev
    Next
    INDEX
    Explanations

    the phrase "decided to" followed by actions or intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    decisions or choices made by individuals

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Detected
    -0.74
    mortem
    -0.72
    thumbnails
    -0.71
    listed
    -0.68
    grain
    -0.67
    database
    -0.66
    finder
    -0.66
     IMAGES
    -0.66
    ritical
    -0.65
    points
    -0.63
    POSITIVE LOGITS
     settle
    1.09
     pursue
    1.06
     postpone
    1.00
     ignore
    0.96
     adopt
    0.96
     give
    0.96
     capitalize
    0.96
     avoid
    0.96
     maximize
    0.96
     donate
    0.96
    Activations Density 0.079%

    No Known Activations