© 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. 7082
    Prev
    Next
    INDEX
    Explanations

    words related to opinions or viewpoints

    oai_token-act-pair · gpt-3.5-turbo

    phrases relating to perceptions or judgments about entities or concepts

    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
    plan
    -0.68
    ften
    -0.66
    vous
    -0.64
    backer
    -0.64
    mouth
    -0.61
     afore
    -0.61
    fts
    -0.60
    load
    -0.59
    nown
    -0.57
     Frie
    -0.57
    POSITIVE LOGITS
     favorably
    0.93
    phas
    0.82
    wcsstore
    0.77
    ById
    0.75
    ĸ
    0.73
    opian
    0.72
    æĦ
    0.72
    ibly
    0.68
    awed
    0.68
     negatively
    0.68
    Activations Density 0.055%

    No Known Activations