INDEX

Explanations

elements related to questioning and uncertainty

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

-0.98

 Jefus

-0.97

IsMutable

-0.95

 HasFactory

-0.95

ⓧ

-0.89

 Perſ

-0.85

neſs

-0.85

 ComVisible

-0.84

 itſelf

-0.83

 Reſ

-0.83

POSITIVE LOGITS

 have

0.63

get

0.58

 just

0.57

 never

0.57

hat

0.56

can

0.55

 Just

0.55

see

0.54

0.52

 they

0.51

Activations Density 0.209%

elements related to questioning and uncertainty

No Comments

No Known Activations