INDEX

Explanations

references to historical figures and military leaders within a specific historical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/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.20.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

脚注の使い方

-0.64

 Inflate

-0.54

TagMode

-0.51

BindView

-0.51

Hochspringen

-0.51

MockBean

-0.51

 Bourgoin

-0.51

 MotionEvent

-0.50

Ney

-0.50

displayquote

-0.48

POSITIVE LOGITS

InitVars

0.77

RenderAtEndOf

0.56

Byz

0.54

 Vandal

0.52

 defray

0.52

 Nirvana

0.51

DMV

0.51

 fubject

0.50

DataAdapter

0.50

Configurer

0.50

Activations Density 0.203%

references to historical figures and military leaders within a specific historical context

No Comments

No Known Activations