INDEX

Explanations

symbols and formatting elements used in textual or coding contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 where

-0.50

 ffilm

-0.47

tagHelper

-0.47

where

-0.46

udar

-0.45

 оригіналу

-0.45

✭✭

-0.45

dru

-0.44

ˏ

-0.44

WithIdentifier

-0.43

POSITIVE LOGITS

 ostavi

0.85

లాలు

0.77

afficheront

0.72

RegressionTest

0.70

 oprot

0.69

 BitSet

0.68

 referenties

0.67

appé

0.65

 EconPapers

0.64

 Закон

0.64

Activations Density 0.194%

symbols and formatting elements used in textual or coding contexts

No Comments

No Known Activations