INDEX

Explanations

numerical identifiers and values

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

 doInBackground

-0.70

"}")

-0.69

хьтан

-0.68

yargs

-0.65

optString

-0.61

webElementXpaths

-0.60

éd

-0.59

([(

-0.58

Zacks

-0.58

 Réponses

-0.57

POSITIVE LOGITS

didSet

0.68

AnchorStyles

0.64

chmal

0.63

 оригіналу

0.63

EndInit

0.60

Vorlage

0.58

getMenuInflater

0.58

toHave

0.57

Wasn

0.55

 Aristi

0.54

Activations Density 0.067%

numerical identifiers and values

No Comments

No Known Activations