INDEX

Explanations

words related to programming classes and structures

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

 Monfieur

-0.87

 pleaſure

-0.79

Tikang

-0.78

 ſever

-0.77

 myſelf

-0.77

EDEFAULT

-0.74

出版年

-0.74

 uſed

-0.74

SequentialGroup

-0.74

+#+

-0.73

POSITIVE LOGITS

ranslated

0.43

 migli

0.43

0.42

<=>

0.41

0.40

 entanto

0.40

 laterales

0.39

เภ

0.38

osa

0.38

 physical

0.38

Activations Density 0.381%

words related to programming classes and structures

No Comments

No Known Activations