INDEX

Explanations

terms associated with specific identifiers or locations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

and

-0.54

BITS

-0.47

 personal

-0.45

pement

-0.44

etc

-0.43

heti

-0.42

等の

-0.42

 chi̍t

-0.42

らの

-0.41

putBoolean

-0.41

POSITIVE LOGITS

AddTagHelper

0.80

principalColumn

0.78

VersionUID

0.75

 للاسماء

0.74

 estekak

0.71

AnimationsModule

0.71

featureID

0.71

UnusedPrivate

0.70

WaitGroup

0.69

 CiNii

0.69

Activations Density 0.458%

terms associated with specific identifiers or locations

No Comments

No Known Activations