© 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. 0-RES-JB
    11. 16662
    Prev
    Next
    INDEX
    Explanations

    phrases related to digital products and services

    oai_token-act-pair · gpt-3.5-turbo

    words related to accolades or acknowledgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģ®å®
    -0.78
     fertility
    -0.70
     sul
    -0.70
     dates
    -0.69
     sun
    -0.68
     ser
    -0.67
     puls
    -0.66
     Opera
    -0.65
     mobility
    -0.65
     pilgrimage
    -0.62
    POSITIVE LOGITS
    ack
    4.25
    acks
    2.57
    ACK
    2.36
    acking
    1.91
    acked
    1.85
    ackle
    1.81
    acker
    1.66
    ackers
    1.56
    acky
    1.41
    ak
    1.26
    Activations Density 0.010%

    No Known Activations