INDEX

Explanations

terms related to exceeding or surpassing specified values or expectations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 latter

-0.50

 ích

-0.44

зик

-0.43

ek

-0.42

唯

-0.42

JPG

-0.41

 purpose

-0.41

uteri

-0.41

 same

-0.40

 Castello

-0.40

POSITIVE LOGITS

 exceeds

1.14

YOND

1.12

 BEYOND

1.11

 exceeding

1.10

delà

1.08

 surpasses

1.06

 beyond

1.05

 exceed

1.05

 surpassing

1.04

 surpass

1.04

Activations Density 0.395%

terms related to exceeding or surpassing specified values or expectations

No Comments

No Known Activations