© 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. 11495
    Prev
    Next
    INDEX
    Explanations

    references to someone or something being highlighted, showcased, or given special attention in various contexts or media

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "featured" and its variations, indicating media coverage or highlights

    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
     abstinence
    -0.55
    ingham
    -0.54
     lockout
    -0.53
     endurance
    -0.52
     cir
    -0.51
    agos
    -0.51
     patience
    -0.50
     Endurance
    -0.49
     Fah
    -0.49
    cise
    -0.49
    POSITIVE LOGITS
     prominently
    1.50
     alongside
    1.02
     onstage
    0.97
     among
    0.92
     amongst
    0.89
     therein
    0.84
     anywhere
    0.83
    illac
    0.82
     elsewhere
    0.82
     atop
    0.82
    Activations Density 0.345%

    No Known Activations