© 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. 3172
    Prev
    Next
    INDEX
    Explanations

    phrases related to responsibilities and consequences

    oai_token-act-pair · gpt-3.5-turbo

    modal and auxiliary verbs indicating certainty or obligation

    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
    anu
    -0.66
    ft
    -0.66
    aft
    -0.65
     lou
    -0.64
    laus
    -0.64
    oppers
    -0.63
     Hamp
    -0.63
     Hawai
    -0.61
     fishes
    -0.61
    isy
    -0.61
    POSITIVE LOGITS
     actually
    0.93
    ãĤ¦ãĤ¹
    0.84
     probably
    0.83
     exactly
    0.83
     priceless
    0.80
    actly
    0.78
    çī
    0.77
     identical
    0.77
    Ĥİ
    0.76
     awfully
    0.76
    Activations Density 0.376%

    No Known Activations