© 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. 7-RES-JB
    11. 12636
    Prev
    Next
    INDEX
    Explanations

    names, particularly with specific patterns like "Ar___nold" and "A___r___t"

    oai_token-act-pair · gpt-3.5-turbo

    frequently occurring suffixes or segments of the word "Arnold."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nesday
    -0.72
    ascus
    -0.63
    ankind
    -0.60
    glers
    -0.60
    auga
    -0.59
    ancial
    -0.58
     sake
    -0.56
    rers
    -0.55
     lifetime
    -0.54
    inctions
    -0.54
    POSITIVE LOGITS
    inian
    0.77
    itect
    0.75
    ansas
    0.71
    agos
    0.71
    Rah
    0.70
     Cortex
    0.70
    INAL
    0.68
    rary
    0.64
    Correct
    0.64
     Refuge
    0.64
    Activations Density 0.087%

    No Known Activations