© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 11-RES-JB
    11. 10305
    Prev
    Next
    INDEX
    Explanations

    phrases indicating opposing sides or conflicts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "at" followed by a location or context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    planes
    -0.75
    omen
    -0.67
    aceutical
    -0.62
    alities
    -0.59
    OTHER
    -0.56
    adoes
    -0.56
    bender
    -0.55
    selves
    -0.53
    behavior
    -0.53
    hops
    -0.53
    POSITIVE LOGITS
     logger
    1.21
     pains
    1.18
     fault
    1.15
     liberty
    1.14
     odds
    1.06
     ease
    1.01
     least
    1.00
     peace
    0.94
    yp
    0.89
    onement
    0.84
    Activations Density 0.084%

    No Known Activations