INDEX

Explanations

references to eyewitness testimony and observations related to incidents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.12.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

 CreateTagHelper

-0.90

jspx

-0.84

+#+#

-0.83

ArgsConstructor

-0.79

featureID

-0.79

TestingModule

-0.77

NameInMap

-0.75

InstrumentedTest

-0.73

WebElementEntity

-0.73

 morrow

-0.72

POSITIVE LOGITS

UTRAL

0.48

Witnesses

0.47

 Police

0.45

 volunteered

0.44

][/

0.44

 policiales

0.43

stander

0.42

reporter

0.40

querySelector

0.40

 socc

0.39

Activations Density 0.075%

references to eyewitness testimony and observations related to incidents

No Comments

No Known Activations