INDEX

Explanations

code related to function definitions and return statements

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-mlp/layer_22/width_16k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.hook_mlp_out

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

สือ

-0.47

Fro

-0.46

문

-0.43

Dal

-0.42

 հղումներ

-0.42

coroutines

-0.42

 boto

-0.42

lä

-0.42

 enumer

-0.42

SPO

-0.41

POSITIVE LOGITS

 '\\;'

0.92

oredCriteria

0.68

MessageOf

0.68

 abstrait

0.67

évaluateur

0.67

 réparation

0.66

SerializedSize

0.66

 médicaux

0.64

 ainfi

0.63

isContained

0.62

Activations Density 0.044%

code related to function definitions and return statements

No Comments

No Known Activations