© 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. 9979
    Prev
    Next
    INDEX
    Explanations

    first person singular and plural pronouns with words related to personal actions and experiences

    oai_token-act-pair · gpt-3.5-turbo

    personal pronouns and references to individual experiences or actions

    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
    rontal
    -0.77
    heit
    -0.64
    blooded
    -0.62
     targ
    -0.61
     livest
    -0.60
    entric
    -0.60
     enthusi
    -0.59
    puter
    -0.59
    Americ
    -0.59
     Travels
    -0.58
    POSITIVE LOGITS
     Learned
    0.96
     lacks
    0.87
     lacked
    0.86
     REALLY
    0.82
    really
    0.82
     Means
    0.80
     uncovered
    0.80
     really
    0.80
     missing
    0.79
     mean
    0.77
    Activations Density 0.092%

    No Known Activations