INDEX

Explanations

phrases indicating historical context or significant past events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

aarrggbb

-0.61

styleType

-0.59

ⓧ

-0.58

Chham

-0.55

évaluateur

-0.55

Manbalar

-0.54

RUnlock

-0.52

 kiệm

-0.52

 kaynağından

-0.52

TokenNameRPAREN

-0.51

POSITIVE LOGITS

 decades

0.59

 past

0.50

 years

0.45

 geçmiş

0.44

decade

0.41

 postwar

0.41

 centuries

0.40

 siglo

0.38

 yıllar

0.37

 ancient

0.36

Activations Density 0.510%

phrases indicating historical context or significant past events

No Comments

No Known Activations