© 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. 14863
    Prev
    Next
    INDEX
    Explanations

    words related to barriers or obstacles

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "oll"

    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
     Ars
    -0.73
     attend
    -0.62
     spe
    -0.62
     related
    -0.62
     beats
    -0.62
     affiliated
    -0.59
     Hardcore
    -0.58
     Ares
    -0.57
     drive
    -0.57
     equivalent
    -0.56
    POSITIVE LOGITS
    oll
    4.41
    olls
    3.24
    olla
    1.71
    oller
    1.58
    olly
    1.48
    ollo
    1.33
    ollen
    1.20
    oli
    1.18
    ollar
    1.15
    ull
    1.15
    Activations Density 0.018%

    No Known Activations