INDEX

Explanations

terms related to grievances and complaints, particularly in a legal or institutional context

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

SourceChecksum

-0.89

+#+#

-0.84

rawDesc

-0.71

 cherchés

-0.68

RegressionTest

-0.68

.$_

-0.67

EndProject

-0.66

 Taktlose

-0.65

 nonUne

-0.64

IsContent

-0.63

POSITIVE LOGITS

 reporting

0.63

 segnal

0.60

 alert

0.56

 alerting

0.55

 whistle

0.55

enumi

0.54

 alerted

0.53

Enllaces

0.53

 whist

0.51

 anonymously

0.51

Activations Density 0.362%

terms related to grievances and complaints, particularly in a legal or institutional context

No Comments

No Known Activations