INDEX

Explanations

words related to positive sentiment and reinforcement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 onCreateView

-1.01

MigrationBuilder

-0.87

Chham

-0.78

 Familienname

-0.78

ContentAsync

-0.76

enterOuterAlt

-0.76

 estekak

-0.76

ICEF

-0.75

 initComponents

-0.75

ÍTULO

-0.72

POSITIVE LOGITS

bad

0.70

0.60

 plus

0.57

Plus

0.56

iv

0.56

Bad

0.55

Dom

0.55

plus

0.55

bad

0.53

0.51

Activations Density 0.215%

words related to positive sentiment and reinforcement

No Comments

No Known Activations