© 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. 11063
    Prev
    Next
    INDEX
    Explanations

    personal pronouns referring to oneself

    oai_token-act-pair · gpt-3.5-turbo

    personal references or subjective expressions of experience

    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
     tests
    -0.65
     envelope
    -0.65
     unfinished
    -0.64
    umption
    -0.63
     functionality
    -0.63
     gratification
    -0.62
     sunset
    -0.62
     scales
    -0.62
     storage
    -0.62
     pollut
    -0.62
    POSITIVE LOGITS
     whom
    1.27
    who
    1.19
    untled
    1.00
    friends
    1.00
     individuals
    0.99
    selves
    0.99
    those
    0.96
     representatives
    0.95
     acquaintances
    0.95
     yourselves
    0.95
    Activations Density 0.487%

    No Known Activations