INDEX

Explanations

numerical sequences related to identification or recall numbers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/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.17.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

 AppModule

-0.67

 rospy

-0.64

ARROLL

-0.59

}$

-0.58

CppMethod

-0.58

estacks

-0.55

ARROLLO

-0.55

rizona

-0.54

 виправивши

-0.54

 externi

-0.54

POSITIVE LOGITS

ArgsConstructor

0.61

Nationalité

0.48

adaptiveStyles

0.46

MLLoader

0.46

back

0.45

잡

0.43

 doğ

0.42

puts

0.42

CodeDom

0.41

клопе

0.41

Activations Density 0.731%

numerical sequences related to identification or recall numbers

No Comments

No Known Activations