© 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. 3353
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names of people

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns and contractions related to individuals

    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
    trop
    -0.73
    ãĥ´ãĤ¡
    -0.73
    adan
    -0.73
    ãĥķãĤ¡
    -0.72
    galitarian
    -0.71
    deals
    -0.71
    agree
    -0.69
    flex
    -0.69
     Pengu
    -0.69
    ÙIJ
    -0.68
    POSITIVE LOGITS
     whereabouts
    1.38
     belongings
    1.29
     plight
    1.22
     disappearance
    1.21
     ordeal
    1.12
     lawyer
    1.11
     fate
    1.11
     attorney
    1.11
     father
    1.09
     assailant
    1.08
    Activations Density 0.267%

    No Known Activations