INDEX

Explanations

phrases related to existential or introspective questions about self-awareness and identity

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 preced

-0.59

 alcanzó

-0.55

 démocr

-0.52

 sufficient

-0.50

 énergé

-0.49

Lors

-0.48

Datuak

-0.48

AFFIRMED

-0.48

 survives

-0.48

 Sump

-0.47

POSITIVE LOGITS

 doing

0.88

 looking

0.84

 making

0.83

 trying

0.83

)‏

0.83

tvguidetime

0.83

正在

0.82

 going

0.81

 đang

0.78

 Estou

0.78

Activations Density 0.374%

phrases related to existential or introspective questions about self-awareness and identity

No Comments

No Known Activations