INDEX

Explanations

verbs indicating past actions or experiences related to investment and improvements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 Réponses

-0.74

yntaxException

-0.71

MethodManager

-0.67

سمبر

-0.60

 فريبيس

-0.60

ButterKnife

-0.58

 للاسماء

-0.57

ConstraintMaker

-0.56

 HasFactory

-0.56

atherapy

-0.55

POSITIVE LOGITS

 historically

0.62

 increasingly

0.58

 proven

0.56

 sometimes

0.56

 longtemps

0.56

σχ

0.53

 traditionally

0.53

 never

0.52

 tended

0.52

 tends

0.51

Activations Density 0.255%

verbs indicating past actions or experiences related to investment and improvements

No Comments

No Known Activations