INDEX

Explanations

negative phrases related to experiences or evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/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.20.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

 pinulongan

-0.61

StructEnd

-0.59

WriteTagHelper

-0.59

хьтан

-0.57

protoc

-0.55

findpost

-0.55

:✨

-0.55

tonode

-0.53

 للاسماء

-0.52

SizeF

-0.52

POSITIVE LOGITS

enumi

0.64

 miglior

0.55

 fault

0.54

 happier

0.54

XmlRootElement

0.54

 wrong

0.53

mejor

0.50

 brass

0.50

Wrong

0.50

 résister

0.49

Activations Density 0.080%

negative phrases related to experiences or evaluations

No Comments

No Known Activations