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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10051
    Prev
    Next
    INDEX
    Explanations

    comparative phrases using "might as well" or "could just as easily"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express similarity or comparison

    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
    roads
    -0.63
    arial
    -0.61
    tsky
    -0.61
    oresc
    -0.59
     briefs
    -0.59
    lining
    -0.58
     Reporting
    -0.56
    allery
    -0.55
     Madagascar
    -0.55
    acent
    -0.55
    POSITIVE LOGITS
     well
    1.32
    well
    1.16
    phy
    0.89
     easily
    0.88
    ym
    0.83
    semble
    0.83
     Well
    0.82
    Well
    0.81
     plaus
    0.79
    ynchron
    0.78
    Activations Density 0.034%

    No Known Activations