INDEX

Explanations

sections of text with no significant content or relevant information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

psum

-0.58

VersionUID

-0.57

($__

-0.53

 مؤرشف

-0.47

illium

-0.47

“

-0.45

gatsby

-0.44

velocityX

-0.44

CompleteListener

-0.44

cupertino

-0.43

POSITIVE LOGITS

parsedMessage

1.20

expandindo

1.16

 beginnetje

1.08

 виправивши

0.99

IUrlHelper

0.98

rungsseite

0.94

 bezeichneter

0.85

providedIn

0.83

bewerken

0.81

verwijspagina

0.81

Activations Density 0.037%

sections of text with no significant content or relevant information

No Comments

No Known Activations