© 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. 2860
    Prev
    Next
    INDEX
    Explanations

    keywords related to breaking or separation

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to breaks or interruptions

    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
    IFIED
    -0.64
    ãĥĺãĥ©
    -0.60
     murd
    -0.59
    MSN
    -0.59
    itatively
    -0.59
     Majority
    -0.58
     assass
    -0.58
    ifice
    -0.58
     complexion
    -0.58
     blat
    -0.56
    POSITIVE LOGITS
    away
    1.42
    neck
    1.41
    fast
    1.30
    aways
    1.13
    through
    1.09
    points
    1.07
    water
    1.00
    beat
    1.00
    point
    0.96
    waters
    0.96
    Activations Density 0.034%

    No Known Activations