INDEX

Explanations

phrases indicating uncertainty or incomplete thoughts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 utafitiHapana

-0.73

chik

-0.57

 transfieras

-0.54

évaluateur

-0.51

iel

-0.51

ote

-0.51

gyar

-0.48

INOS

-0.47

ABETH

-0.47

 ITIS

-0.47

POSITIVE LOGITS

 ModelExpression

0.66

+:+

0.63

GEBURTSDATUM

0.62

Personendaten

0.61

expandindo

0.59

ArgsConstructor

0.59

LabelTagHelper

0.58

insee

0.58

UnknownFields

0.56

Bakgrunnsstoff

0.55

Activations Density 0.121%

phrases indicating uncertainty or incomplete thoughts

No Comments

No Known Activations