INDEX

Explanations

truth statements and evaluations of accuracy

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Bernadette

-0.91

 Monfieur

-0.86

 ejus

-0.78

 يتيمه

-0.77

Ivo

-0.75

 Noche

-0.75

 Jove

-0.75

 îles

-0.74

 صوتيه

-0.72

 poži

-0.71

POSITIVE LOGITS

stdbool

1.14

 True

1.11

 true

1.10

Tru

1.07

 TRUE

1.05

Tru

0.99

True

0.90

isTrue

0.89

TRUE

0.87

 Trujillo

0.82

Activations Density 0.089%

truth statements and evaluations of accuracy

No Comments

No Known Activations