INDEX

Explanations

phrases indicating central alignment or positioning

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

 विश्वसनीयता

-0.85

expandindo

-0.84

 مرئيه

-0.74

Vidite

-0.70

 betweenstory

-0.68

 '\\;'

-0.68

 smtplib

-0.64

 Javan

-0.63

 Adagio

-0.62

 secrets

-0.62

POSITIVE LOGITS

 middle

0.87

center

0.83

 centro

0.76

centre

0.73

middle

0.71

 centre

0.69

 center

0.68

 marking

0.66

imageshack

0.63

centers

0.62

Activations Density 0.108%

phrases indicating central alignment or positioning

No Comments

No Known Activations