INDEX

Explanations

references to efforts made in various contexts

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

 חיצוניים

-0.83

UVWXYZ

-0.78

PSM

-0.76

 يتيمه

-0.76

yntaxException

-0.73

hermosa

-0.69

,$_

-0.69

 solvable

-0.69

 HttpNotFound

-0.69

odeon

-0.67

POSITIVE LOGITS

 effort

1.92

 efforts

1.86

 Effort

1.84

 Efforts

1.77

Effort

1.63

EFF

1.51

effort

1.50

efforts

1.47

 attempts

1.24

Ef

1.12

Activations Density 0.053%

references to efforts made in various contexts

No Comments

No Known Activations