INDEX

Explanations

recommendations for books or resources aimed at helping others

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 мәкал

-0.57

reibung

-0.57

الدراسه

-0.51

verläs

-0.49

tvguidetime

-0.49

erialization

-0.49

따

-0.49

 certi

-0.48

ridos

-0.48

ὶ

-0.48

POSITIVE LOGITS

ConstraintMaker

0.56

scalatest

0.56

StoryboardSegue

0.55

tagHelperRunner

0.54

 saites

0.53

AndroidJUnit

0.53

 synes

0.52

WaitGroup

0.51

WebControls

0.50

BufferException

0.49

Activations Density 0.188%

recommendations for books or resources aimed at helping others

No Comments

No Known Activations