INDEX

Explanations

keywords and concepts related to computer programming and declarations in code

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

 utafitiHapana

-0.60

Geplaatst

-0.55

 JpaRepository

-0.54

 onOptions

-0.54

encodeWith

-0.54

 oprot

-0.50

 udaler

-0.49

nodoc

-0.49

 оригіналу

-0.49

 Carroll

-0.49

POSITIVE LOGITS

 variable

1.54

 variables

1.45

 Variable

1.44

Variable

1.42

variable

1.38

 Variables

1.35

变量

1.30

variables

1.28

Variables

1.25

 VARIABLE

1.22

Activations Density 0.749%

keywords and concepts related to computer programming and declarations in code

No Comments

No Known Activations