© 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. 2-RES-JB
    11. 5799
    Prev
    Next
    INDEX
    Explanations

    references to the word "Merciful" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Merc" and related terms, likely in a financial or mercantile context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FORMATION
    -0.84
    doors
    -0.82
    eking
    -0.76
    growth
    -0.75
    cki
    -0.72
    ¥µ
    -0.71
    Traditional
    -0.69
    åĤ
    -0.69
    case
    -0.67
     Kimmel
    -0.67
    POSITIVE LOGITS
    enaries
    1.34
    iless
    1.23
     simultane
    1.02
    uria
    1.00
    ifully
    0.99
    opol
    0.93
    urious
    0.90
    uries
    0.89
     oun
    0.88
     destro
    0.88
    Activations Density 0.006%

    No Known Activations