INDEX

Explanations

specific classifications or identifiers related to programming or metadata

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 caccia

-0.52

énario

-0.52

 tavola

-0.51

 morire

-0.49

niosek

-0.48

COMPLE

-0.48

onActivityResult

-0.48

 viață

-0.48

wix

-0.46

ể

-0.45

POSITIVE LOGITS

3.62

1.74

1.20

1.12

1.05

tagHelperRunner

1.03

########.

0.97

0.96

 EconPapers

0.86

parsedMessage

0.85

Activations Density 0.018%

specific classifications or identifiers related to programming or metadata

No Comments

No Known Activations