© 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. 10-RES-JB
    11. 11278
    Prev
    Next
    INDEX
    Explanations

    personal pronouns followed by past tense action verbs

    oai_token-act-pair · gpt-3.5-turbo

    pronouns and references to characters in a narrative

    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
     intervening
    -0.70
    ythm
    -0.70
     departures
    -0.70
    phasis
    -0.67
    focus
    -0.66
    Independent
    -0.66
    jri
    -0.66
     Compensation
    -0.66
     contrasts
    -0.65
    phas
    -0.65
    POSITIVE LOGITS
     stole
    1.11
     collected
    0.97
     wore
    0.97
     stash
    0.97
     purchased
    0.96
     stored
    0.96
     deposited
    0.94
     bought
    0.92
     confiscated
    0.92
     retrieved
    0.91
    Activations Density 0.166%

    No Known Activations