INDEX

Explanations

references to numerical values and legal terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 <<<<<<<<<<<<<<

-0.61

Scénario

-0.57

 Waray

-0.56

heça

-0.54

новниш

-0.53

werd

-0.50

visor

-0.50

 jScrollPane

-0.49

principalTable

-0.49

сія

-0.48

POSITIVE LOGITS

moveToFirst

0.56

peicher

0.55

 studenten

0.54

RegistryLite

0.54

 disponibilités

0.53

uldade

0.52

GOTREF

0.52

دانشنامهٔ

0.51

WithIOException

0.51

 estratég

0.50

Activations Density 0.108%

references to numerical values and legal terminology

No Comments

No Known Activations