© 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. 12761
    Prev
    Next
    INDEX
    Explanations

    pronouns and main verbs in reported speech

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "he" in various contexts

    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
     Dominion
    -0.66
    fail
    -0.63
     Hive
    -0.62
     Mandatory
    -0.62
     Entry
    -0.57
    ogue
    -0.56
     Header
    -0.56
     AAA
    -0.56
     Six
    -0.56
     Fail
    -0.55
    POSITIVE LOGITS
     regretted
    1.27
     expects
    1.25
     believes
    1.24
     understands
    1.22
    'd
    1.19
     hoped
    1.17
     thinks
    1.17
     regrets
    1.16
     intends
    1.15
     disagrees
    1.13
    Activations Density 0.132%

    No Known Activations