© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 23273
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and some verbs related to actions or states

    oai_token-act-pair · gpt-3.5-turbo

    pronouns indicating subjects and objects in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aukee
    -0.81
    ãĤ´ãĥ³
    -0.74
    yip
    -0.72
    Skip
    -0.63
    icist
    -0.60
    insula
    -0.57
    isher
    -0.57
     Dayton
    -0.57
     practition
    -0.57
     Moroc
    -0.57
    POSITIVE LOGITS
     consequently
    1.23
     certainly
    1.23
     accordingly
    1.14
     therefore
    1.11
    'll
    1.03
     definitely
    1.00
     deserve
    1.00
     intend
    0.99
     rightfully
    0.90
     frankly
    0.90
    Activations Density 0.204%

    No Known Activations