© 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. 11-RES-JB
    11. 23611
    Prev
    Next
    INDEX
    Explanations

    phrases where the word "by" is used in conjunction with a particular context or action

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate causation or attribution

    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
    bian
    -0.64
    umble
    -0.64
    amera
    -0.63
    halla
    -0.63
    igi
    -0.60
    HQ
    -0.60
    aukee
    -0.59
    regon
    -0.58
    ptions
    -0.57
    bps
    -0.56
    POSITIVE LOGITS
    products
    1.38
     definition
    1.29
    product
    1.22
     implication
    1.20
     virtue
    1.17
    gone
    1.08
     extension
    1.05
     default
    1.04
    catch
    1.04
    laws
    1.02
    Activations Density 0.077%

    No Known Activations