INDEX

Explanations

arguments concerning beliefs and opinions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 supuestamente

-0.68

 supposedly

-0.48

 reportedly

-0.47

 allegedly

-0.47

Apparently

-0.45

 Apparently

-0.45

Said

-0.45

<eos>

-0.44

 prétend

-0.44

 lecz

-0.44

POSITIVE LOGITS

 فريبيس

1.27

enumii

0.96

FieldBuilder

0.90

featureID

0.90

клопе

0.88

 MainAxisSize

0.88

########.

0.86

 ویکی‌پدیای

0.85

WebElementEntity

0.84

MessageTagHelper

0.84

Activations Density 0.327%

arguments concerning beliefs and opinions

No Comments

No Known Activations