INDEX

Explanations

referenced code and programming constructs related to data handling and manipulation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

weil

-0.54

이버

-0.51

Set

-0.48

wijl

-0.48

 occupa

-0.47

 vọng

-0.45

 nhàng

-0.44

 لئے

-0.44

บุรี

-0.43

 weber

-0.41

POSITIVE LOGITS

tvguidetime

0.92

AddTagHelper

0.89

ffions

0.87

 MainAxisSize

0.85

RenderAtEndOf

0.84

 تضيفلها

0.83

processable

0.79

]='\

0.78

UserScript

0.78

PreferredItem

0.77

Activations Density 1.266%

referenced code and programming constructs related to data handling and manipulation

No Comments

No Known Activations