© 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. 331
    Prev
    Next
    INDEX
    Explanations

    complex compound words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    words or prefixes related to varied professions and actions

    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
     Trin
    -0.70
    è£ħ
    -0.70
    ivo
    -0.69
    PH
    -0.68
    stellar
    -0.66
    doi
    -0.63
     transitional
    -0.61
    sym
    -0.61
    PAC
    -0.61
    FUL
    -0.61
    POSITIVE LOGITS
    acters
    1.04
    oldown
    0.94
    usters
    0.88
    akery
    0.86
    utters
    0.82
    ppers
    0.80
    ards
    0.79
    sts
    0.77
    asers
    0.76
    ilities
    0.75
    Activations Density 0.117%

    No Known Activations