INDEX

Explanations

mentions of specific coding entities or programming concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

NUMX

-1.01

IBOutlet

-0.95

]")]

-0.93

mybatisplus

-0.90

 Chwiliwch

-0.88

#+#

-0.88

RectangleBorder

-0.88

évaluateur

-0.86

脚注の使い方

-0.83

 Мексичка

-0.82

POSITIVE LOGITS

my

0.50

is

0.49

...

0.49

0.47

ung

0.43

 حم

0.42

then

0.41

مان

0.40

op

0.40

Activations Density 0.108%

mentions of specific coding entities or programming concepts

No Comments

No Known Activations