INDEX

Explanations

references to the term "Cal" or variations thereof

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

RepeatedField

-0.73

AndEndTag

-0.72

-0.71

IUrlHelper

-0.71

 IndexError

-0.70

 שוליים

-0.70

AndroidJUnit

-0.68

IsContent

-0.66

 Espagne

-0.66

Obrázky

-0.66

POSITIVE LOGITS

Cal

3.95

Cal

3.67

cal

3.56

cal

3.30

CAL

3.04

CAL

2.93

Kal

1.79

kal

1.76

 Cali

1.71

 Calder

1.61

Activations Density 0.038%

references to the term "Cal" or variations thereof

No Comments

No Known Activations