INDEX

Explanations

informational content related to news broadcasts and broadcasts themselves

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 conci

-0.29

 avanzado

-0.29

 avan

-0.28

 znan

-0.28

Utd

-0.28

 Avan

-0.27

ležit

-0.26

渋

-0.26

__()

-0.26

 raggiung

-0.26

POSITIVE LOGITS

AutoScaleMode

0.66

 VIDEOTAPE

0.66

 שוליים

0.65

Viited

0.64

DockStyle

0.60

interopRequire

0.59

rungsseite

0.59

VYMaps

0.57

SOUNDBITE

0.57

Зноскі

0.56

Activations Density 0.290%

informational content related to news broadcasts and broadcasts themselves

No Comments

No Known Activations