© 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. 18730
    Prev
    Next
    INDEX
    Explanations

    overlapping terms related to computer technology and common words with the prefix "over-"

    oai_token-act-pair · gpt-3.5-turbo

    the term "Over" in various contexts

    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
     partName
    -0.65
    uments
    -0.61
     Retrieved
    -0.61
    UES
    -0.60
     firsthand
    -0.60
    gling
    -0.59
    ILY
    -0.58
    egal
    -0.57
    oooooooo
    -0.57
    arium
    -0.57
    POSITIVE LOGITS
    lay
    1.22
    drive
    1.22
    ride
    1.20
    flow
    1.18
    lap
    1.14
    lord
    1.12
    due
    1.11
    kill
    1.09
    growth
    1.09
    haul
    1.07
    Activations Density 0.045%

    No Known Activations