INDEX

Explanations

the specific term "par" in various forms and contexts

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

The token "par" followed by certain letters

np_acts-logits-general · gemini-2.0-flash

words starting with par

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

Filmografie

-0.55

 scope

-0.52

modb

-0.51

 character

-0.49

bpp

-0.48

ikaze

-0.48

fiehlt

-0.48

 Metode

-0.47

 tưởng

-0.46

Clasificación

-0.46

POSITIVE LOGITS

+#+#

0.65

IBOutlet

0.58

 IBOutlet

0.58

 CGRectMake

0.55

InjectAttribute

0.52

تقاوى

0.51

WriteTagHelper

0.51

Datuak

0.50

Par

0.49

PAR

0.49

Activations Density 0.112%

the specific term "par" in various forms and contexts

The token "par" followed by certain letters

words starting with par

No Comments

No Known Activations