INDEX

Explanations

terms related to decision-making and options

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 Peralta

-0.78

 îna

-0.78

nails

-0.75

indrome

-0.75

Tembelea

-0.74

helial

-0.74

"}>

-0.73

 appellants

-0.72

virons

-0.71

 viață

-0.71

POSITIVE LOGITS

 Choices

1.76

 choices

1.75

 Choice

1.66

 choice

1.62

 CHOICE

1.61

Choices

1.58

choices

1.52

Choice

1.50

choice

1.45

CHOICE

1.45

Activations Density 0.055%

terms related to decision-making and options

No Comments

No Known Activations