© 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. 4226
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names of specific entities

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate something is commonly referred to or known by a specific name or title

    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
    SPONSORED
    -0.82
    Edited
    -0.66
    azaki
    -0.64
    eor
    -0.64
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.62
    atche
    -0.62
    reau
    -0.62
    arnaev
    -0.61
    ongyang
    -0.61
     conclud
    -0.61
    POSITIVE LOGITS
     COP
    0.80
    pires
    0.76
     Operation
    0.73
     "#
    0.73
     Excellence
    0.71
     Maid
    0.70
     "
    0.69
     Punch
    0.67
     Fin
    0.66
    phe
    0.64
    Activations Density 0.058%

    No Known Activations