© 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. 20372
    Prev
    Next
    INDEX
    Explanations

    personal pronouns followed by verbs in the past tense

    oai_token-act-pair · gpt-3.5-turbo

    instances of the pronoun "he."

    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
    noon
    -0.68
     privile
    -0.66
     miscarriage
    -0.66
    Measure
    -0.62
     cannabin
    -0.62
     Sorce
    -0.59
     witchcraft
    -0.58
     caliber
    -0.57
     expiration
    -0.57
     Measure
    -0.56
    POSITIVE LOGITS
     said
    1.43
     wrote
    1.32
     explained
    1.22
     joked
    1.20
     told
    1.19
     added
    1.16
     says
    1.14
    said
    1.14
     tweeted
    1.12
     remarked
    1.10
    Activations Density 0.071%

    No Known Activations