INDEX

Explanations

terms indicating significance or necessity in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

LookAnd

-0.64

 BrowserModule

-0.54

 Spisak

-0.52

гӀ

-0.52

ウンサー

-0.51

ResponseWriter

-0.50

 QUART

-0.50

beginTransaction

-0.50

quiao

-0.49

шта

-0.49

POSITIVE LOGITS

 crucial

1.24

 important

1.22

 importance

1.16

 essential

1.13

 vital

1.08

 Crucial

1.06

 Important

1.05

important

1.04

 Importance

1.00

essential

0.98

Activations Density 0.275%

terms indicating significance or necessity in various contexts

No Comments

No Known Activations