INDEX

Explanations

expressions of emotional reactions and feedback

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/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.14.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

 فريبيس

-0.98

UserScript

-0.90

 незавершена

-0.89

/**

-0.86

GEBURTSDATUM

-0.86

UnsafeEnabled

-0.85

 consultato

-0.83

 StringTokenizer

-0.81

 صوتيه

-0.81

sizeCache

-0.81

POSITIVE LOGITS

0.47

ha

0.45

0.44

迫

0.43

0.42

0.41

↵↵

0.41

well

0.41

たの

0.41

ciaio

0.40

Activations Density 0.122%

expressions of emotional reactions and feedback

No Comments

No Known Activations