INDEX

Explanations

references to the concept of truth

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

Tembelea

-0.78

ⓧ

-0.77

 unfavourable

-0.76

 Kenney

-0.75

 suivants

-0.75

canActivate

-0.74

glBindTexture

-0.73

'{@

-0.72

גרת

-0.72

QPalette

-0.71

POSITIVE LOGITS

 truth

2.17

 Truth

2.16

truth

2.08

Truth

2.00

 TRUTH

1.99

 truths

1.75

 Truths

1.54

 verdad

1.22

 verità

1.20

 Wahrheit

1.19

Activations Density 0.036%

references to the concept of truth

No Comments

No Known Activations