INDEX

Explanations

references to children and their related issues or characteristics

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

 myſelf

-1.03

Efq

-0.99

 pleaſure

-0.92

 uſed

-0.90

StructEnd

-0.89

 itſelf

-0.89

adaptiveStyles

-0.88

 raiſ

-0.86

 للاسماء

-0.86

 оригіналу

-0.85

POSITIVE LOGITS

 Child

1.21

Child

1.08

 child

0.99

 CHILD

0.77

child

0.69

CHILD

0.69

0.67

Ch

0.66

0.64

war

0.64

Activations Density 0.239%

references to children and their related issues or characteristics

No Comments

No Known Activations