© 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. 10-RES-JB
    6. 17462
    Prev
    Next
    INDEX
    Explanations

    mentions of historical figures and events

    oai_token-act-pair · gpt-3.5-turbo

    references to historical texts and accounts

    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
    CEO
    -0.80
    afety
    -0.74
     hurting
    -0.74
    docker
    -0.73
     maximizing
    -0.73
     NCT
    -0.73
    cancer
    -0.72
    oppable
    -0.72
     AWS
    -0.71
     Affordable
    -0.70
    POSITIVE LOGITS
     interpol
    1.27
     extant
    1.24
     manuscripts
    1.22
     textual
    1.20
     contempor
    1.18
     histor
    1.14
     historians
    1.12
     earliest
    1.11
     inscription
    1.09
     archaeological
    1.08
    Activations Density 0.498%

    No Known Activations