INDEX

Explanations

references to formatting data or strings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 OFDb

-0.87

contentLoaded

-0.75

 methodName

-0.72

 виправивши

-0.69

ViewImports

-0.69

StoryboardSegue

-0.67

ImageContext

-0.66

MergeFrom

-0.66

RTLD

-0.65

intenant

-0.64

POSITIVE LOGITS

format

1.20

WithFormat

0.97

FORMAT

0.81

Format

0.77

Sprintf

0.72

fprintf

0.69

scanf

0.64

 Format

0.63

 format

0.59

对自己

0.57

Activations Density 0.038%

references to formatting data or strings

No Comments

No Known Activations