INDEX

Explanations

dates or time-related references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 Jefus

-0.71

felves

-0.67

 houſe

-0.65

 Diſ

-0.63

 Houſe

-0.63

 contigo

-0.63

tvguidetime

-0.63

nefs

-0.62

wiſe

-0.60

 chofe

-0.59

POSITIVE LOGITS

GeneratedCode

0.74

 ostavi

0.63

contentLoaded

0.63

 دیکھیے

0.58

DeleteBehavior

0.58

substack

0.57

0.56

 protoimpl

0.56

//

0.56

pushFollow

0.56

Activations Density 0.122%

dates or time-related references

No Comments

No Known Activations