INDEX

Explanations

phrases that highlight belief systems and choices

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

Personensuche

-0.80

SizeF

-0.70

ollectionView

-0.60

AnchorStyles

-0.58

Eloquent

-0.56

참고

-0.55

 keting

-0.54

 ResponseEntity

-0.53

HtmlAttribute

-0.51

Erfolge

-0.51

POSITIVE LOGITS

 accompany

1.08

 accompanies

1.00

 underlie

0.98

 underlies

0.96

 characterizes

0.90

 adorn

0.90

 characterize

0.90

 dominate

0.89

 populate

0.89

 inhabit

0.83

Activations Density 0.567%

phrases that highlight belief systems and choices

No Comments

No Known Activations