INDEX

Explanations

start and end markers of sections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

awtextra

-1.01

jsii

-0.97

protoimpl

-0.86

Jeografia

-0.80

fjspx

-0.80

ⓘ

-0.78

 onOptions

-0.75

 uncomment

-0.75

elemField

-0.73

rungsseite

-0.73

POSITIVE LOGITS

ñora

0.48

↵

0.48

0.46

važ

0.46

 Geschle

0.46

ayuno

0.46

 quelconque

0.45

 volont

0.45

 håll

0.44

evaluator

0.44

Activations Density 0.009%

start and end markers of sections

No Comments

No Known Activations