© 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. 11-RES-JB
    11. 490
    Prev
    Next
    INDEX
    Explanations

    the pronoun 'I' followed by verbs

    oai_token-act-pair · gpt-3.5-turbo

    instances of the pronoun "I" and expressions of personal experience or feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yip
    -0.74
    pires
    -0.70
    catentry
    -0.61
    Creat
    -0.61
     Emin
    -0.60
    ses
    -0.60
    Recent
    -0.54
     Tiff
    -0.52
    icts
    -0.51
    ieves
    -0.51
    POSITIVE LOGITS
     knew
    1.23
     wasn
    1.14
     hadn
    1.13
    'm
    1.12
     couldn
    1.08
     didn
    1.08
     felt
    1.07
     awoke
    1.07
     realized
    1.07
     waited
    1.05
    Activations Density 0.217%

    No Known Activations