INDEX

Explanations

return statements 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 @ 16-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 varargin

-0.69

 Grecs

-0.65

antaranya

-0.63

 NDEBUG

-0.61

 nonché

-0.60

HasForeignKey

-0.59

 useRouter

-0.58

 rootReducer

-0.55

TagMode

-0.55

CJK

-0.55

POSITIVE LOGITS

tagHelperRunner

0.72

 true

0.64

 false

0.62

 CreateTagHelper

0.62

true

0.61

 True

0.56

false

0.55

лыша

0.53

ielli

0.52

 protoimpl

0.51

Activations Density 0.629%

return statements in code

No Comments

No Known Activations