INDEX

Explanations

expressions related to informative content and personal experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

astify

-0.69

Попис

-0.57

twór

-0.55

Географија

-0.54

锈钢

-0.53

bebe

-0.51

hlon

-0.51

ytale

-0.51

apunov

-0.49

Palabras

-0.49

POSITIVE LOGITS

 informative

1.16

 enlightening

0.98

 interesting

0.98

 useful

0.95

 helpful

0.90

Inform

0.90

inform

0.90

 insightful

0.89

 illuminating

0.88

 Inform

0.86

Activations Density 0.366%

expressions related to informative content and personal experiences

No Comments

No Known Activations