© 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. 0-RES-JB
    11. 16726
    Prev
    Next
    INDEX
    Explanations

    personal statements starting with "My" followed by various statements or descriptions of experiences

    oai_token-act-pair · gpt-3.5-turbo

    the pronoun "My" indicating personal experiences or ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eele
    -0.66
     ideally
    -0.58
    orative
    -0.58
    otics
    -0.58
    ativity
    -0.57
    force
    -0.56
     quo
    -0.56
     conclud
    -0.56
     hemisphere
    -0.56
    urst
    -0.55
    POSITIVE LOGITS
     My
    3.20
    My
    2.35
     MY
    2.01
    my
    1.86
    MY
    1.60
     my
    1.55
     Our
    1.46
     Me
    1.40
     Your
    1.37
     Mine
    1.29
    Activations Density 0.017%

    No Known Activations