INDEX

Explanations

terms related to established or accepted practices and methods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

Mutual

-0.54

 Mutual

-0.51

{}/

-0.48

README

-0.48

MaxWidth

-0.47

mutual

-0.47

iyle

-0.47

 Ganz

-0.46

 toal

-0.45

 сча

-0.45

POSITIVE LOGITS

 established

2.06

 Established

1.92

established

1.76

Established

1.64

 recognised

1.14

 recognized

1.07

 accepted

1.03

 respected

0.98

 acknowledged

0.95

 settled

0.95

Activations Density 0.147%

terms related to established or accepted practices and methods

No Comments

No Known Activations