INDEX

Explanations

terms related to generating processes or chemical reactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

ate

-1.68

ATE

-0.88

ation

-0.83

回

-0.49

まわ

-0.47

 Príncipe

-0.46

colha

-0.45

хьтан

-0.45

chuga

-0.44

UnsafeEnabled

-0.44

POSITIVE LOGITS

 חיצוניים

0.59

SpringBootTest

0.58

 EconPapers

0.58

原始内容存档于

0.57

MLLoader

0.55

IndentedString

0.51

BufferException

0.51

SpringRunner

0.50

ponses

0.49

openConnection

0.48

Activations Density 0.354%

terms related to generating processes or chemical reactions

No Comments

No Known Activations