© 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. 8-RES-JB
    11. 3310
    Prev
    Next
    INDEX
    Explanations

    mentions of individual people or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to individual people or persons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arp
    -0.65
    ãĥ¥
    -0.64
    Bey
    -0.63
     Destination
    -0.63
    PER
    -0.62
     Belt
    -0.62
     Sparrow
    -0.59
     Shore
    -0.59
    Weight
    -0.58
    ãĤ¦ãĤ¹
    -0.58
    POSITIVE LOGITS
    hips
    1.03
    ividual
    1.02
     who
    0.91
    istically
    0.85
     possessing
    0.85
     identifiable
    0.85
    ortium
    0.84
    omal
    0.84
    folk
    0.83
    ourcing
    0.83
    Activations Density 0.065%

    No Known Activations