INDEX

Explanations

the names and titles of individuals, particularly in corporate and organizational contexts

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

Efq

-0.91

 itſelf

-0.82

 myſelf

-0.81

 purpoſe

-0.80

 ſtate

-0.78

 pleaſure

-0.77

 Reſ

-0.77

 Majefty

-0.76

 Diſ

-0.74

 themſelves

-0.73

POSITIVE LOGITS

 تضيفلها

0.71

parsedMessage

0.63

TestBed

0.54

DockStyle

0.53

AutoresizingMask

0.52

 Group

0.52

webElement

0.52

rungsseite

0.52

CEO

0.50

 الي

0.49

Activations Density 0.139%

the names and titles of individuals, particularly in corporate and organizational contexts

No Comments

No Known Activations