INDEX

Explanations

multiple return statements within code snippets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

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

Aholisi

-0.69

brokes

-0.67

 unknownFields

-0.63

anglès

-0.60

Географи

-0.59

cheme

-0.58

PDATE

-0.57

 ICommand

-0.56

ValueStyle

-0.56

ärme

-0.55

POSITIVE LOGITS

return

0.84

ChildScrollView

0.72

 return

0.64

eturn

0.58

 Return

0.54

 FetchType

0.53

testify

0.51

Return

0.50

 returns

0.49

 оригіналу

0.49

Activations Density 0.035%

multiple return statements within code snippets

No Comments

No Known Activations