© 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. 9-RES-JB
    11. 18480
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or descriptions of present or recent events

    oai_token-act-pair · gpt-3.5-turbo

    adverbs that indicate frequency or temporal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onut
    -0.78
    alion
    -0.68
    aily
    -0.65
    ulate
    -0.64
     Patreon
    -0.64
    ottage
    -0.64
    othy
    -0.64
    letico
    -0.63
     Majesty
    -0.62
    eland
    -0.61
    POSITIVE LOGITS
     resembling
    1.13
     employed
    1.11
     attributed
    1.11
     belonging
    1.10
     referred
    1.10
     associated
    1.09
     conceived
    1.06
     represented
    1.05
     undertaken
    1.05
     comprising
    1.03
    Activations Density 0.233%

    No Known Activations