INDEX

Explanations

references to development environments or directories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 InputDecoration

-0.91

彿

-0.78

 '".$

-0.73

ongiorno

-0.71

LabelTagHelper

-0.70

?}",

-0.70

][$

-0.69

HtmlAttribute

-0.69

 rass

-0.67

 Lari

-0.67

POSITIVE LOGITS

dev

2.40

dev

2.26

Dev

2.23

Dev

2.19

DEV

2.11

DEV

2.04

 devs

1.50

devs

1.45

 Devine

1.30

 developer

1.29

Activations Density 0.048%

references to development environments or directories

No Comments

No Known Activations