© 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. 4-RES-JB
    11. 498
    Prev
    Next
    INDEX
    Explanations

    pronouns or nouns related to self-representation or self-identification

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "themselves."

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

    No Comments

    Negative Logits
     Sierra
    -0.72
    aster
    -0.69
     Derby
    -0.67
    amia
    -0.66
    etta
    -0.66
     Fulton
    -0.65
     CASE
    -0.65
     Syndicate
    -0.64
     Rail
    -0.64
     Ki
    -0.64
    POSITIVE LOGITS
    selves
    1.24
     selves
    1.01
     tremend
    0.80
    self
    0.79
     conduc
    0.79
     creatively
    0.78
     underwater
    0.77
     themselves
    0.74
     proport
    0.74
     spontaneously
    0.73
    Activations Density 0.037%

    No Known Activations