INDEX

Explanations

structured data or object attributes, likely in a programming or database context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

ugeot

-1.03

 createSprite

-0.93

Rhestr

-0.91

 SqlCommand

-0.88

 FormsModule

-0.87

ruptedException

-0.86

 FetchType

-0.84

cipy

-0.84

cửa

-0.82

ChildScrollView

-0.82

POSITIVE LOGITS

↵↵

1.73

<h2>

1.51

<h3>

1.34

<blockquote>

1.29

↵↵↵

1.28

↵

1.21

↵↵↵↵

1.19

↵↵↵↵↵

1.16

<strong>

1.16

<eos>

1.15

Activations Density 0.950%

structured data or object attributes, likely in a programming or database context

No Comments

No Known Activations