INDEX

Explanations

phrases indicating agreement or affirmation

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

########.

-0.58

IVEREF

-0.57

SharedDtor

-0.57

#+#

-0.57

CrossRef

-0.56

VideoCapture

-0.54

PMailer

-0.51

 AssemblyProduct

-0.50

 ProtoMessage

-0.50

GEBURTSDATUM

-0.49

POSITIVE LOGITS

arakhand

0.69

tamol

0.69

 AspNetCore

0.68

 unſ

0.63

erdings

0.62

 zufolge

0.62

 zároveň

0.61

 beware

0.60

 AUSSI

0.59

 ladri

0.59

Activations Density 0.175%

phrases indicating agreement or affirmation

No Comments

No Known Activations