INDEX

Explanations

Java AWT (Abstract Window Toolkit) component imports

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

OptionsMenu

-0.55

 calyx

-0.55

 ricar

-0.53

 يتيمه

-0.52

 Theil

-0.52

 IActionResult

-0.52

Demografía

-0.52

UrlResolution

-0.51

φορά

-0.48

 serre

-0.48

POSITIVE LOGITS

awt

0.86

uxxxx

0.70

ValueStyle

0.64

 Walkover

0.63

 autorytatywna

0.61

AutoScaleMode

0.59

tanleria

0.59

dnd

0.59

itinéraire

0.58

ỡng

0.58

Activations Density 0.046%

Java AWT (Abstract Window Toolkit) component imports

No Comments

No Known Activations