INDEX

Explanations

phrases related to claims and benefits processing

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

Following certain words

np_acts-logits-general · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

rungsseite

-0.91

complexContent

-0.87

SourceChecksum

-0.85

已然

-0.84

IsMutable

-0.83

ChildScrollView

-0.82

 protoimpl

-0.81

Примеча

-0.80

矣

-0.79

SharedDtor

-0.79

POSITIVE LOGITS

 lots

0.66

 people

0.59

Lots

0.57

 things

0.54

 kinds

0.52

 everybody

0.51

 sortes

0.49

 Deshalb

0.48

 peuple

0.47

 funny

0.45

Activations Density 2.112%

phrases related to claims and benefits processing

Following certain words

No Comments

No Known Activations