© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 21760
    Prev
    Next
    INDEX
    Explanations

    names or references related to a specific term 'Sin'

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Sin" and its variations in different contexts

    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
    enance
    -0.68
    berman
    -0.67
    ITAL
    -0.62
     NAD
    -0.61
     CONTIN
    -0.60
    sers
    -0.59
     parties
    -0.58
     Melt
    -0.58
     attainment
    -0.58
     Sawyer
    -0.57
    POSITIVE LOGITS
    atra
    1.43
    clair
    1.35
    ews
    1.21
    uous
    1.20
    ners
    1.19
    ister
    1.09
    ew
    1.09
    estro
    1.08
    uously
    1.00
    bad
    0.98
    Activations Density 0.047%

    No Known Activations