© 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. 7-RES-JB
    11. 17136
    Prev
    Next
    INDEX
    Explanations

    pronominal references that indicate personal opinions or experiences

    oai_token-act-pair · gpt-3.5-turbo

    first-person references or expressions of personal opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ministries
    -0.67
    INGTON
    -0.67
     Emin
    -0.64
     vocational
    -0.63
     bureaucratic
    -0.63
     Gutenberg
    -0.62
    Contents
    -0.62
     Kag
    -0.60
    forms
    -0.60
     bureaucracy
    -0.60
    POSITIVE LOGITS
    've
    1.07
    'm
    1.05
    ighed
    1.03
    vantage
    1.00
    'd
    0.90
     presume
    0.89
    xtap
    0.89
    stanbul
    0.88
    'll
    0.87
    ldon
    0.87
    Activations Density 0.345%

    No Known Activations