INDEX

Explanations

phrases indicating a deep understanding or insight into a subject

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

Хьажоргаш

-0.96

IVEREF

-0.95

دانشنامهٔ

-0.87

 Roskov

-0.86

 Wikimedijinoj

-0.86

 Signalez

-0.85

EndGlobalSection

-0.79

WebVitals

-0.77

 ―――――

-0.77

Geplaatst

-0.76

POSITIVE LOGITS

<eos>

0.47

pa

0.44

getElementsBy

0.42

di

0.41

ifndef

0.40

vla

0.40

0.39

二

0.38

َ

0.38

前

0.38

Activations Density 0.135%

phrases indicating a deep understanding or insight into a subject

No Comments

No Known Activations