INDEX

Explanations

white space characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

Datuak

-1.18

 AssemblyTitle

-1.06

IntoConstraints

-1.01

XmlAccessorType

-1.00

 الرياضيه

-0.97

 صوتيه

-0.97

قایناقلار

-0.97

 للمعارف

-0.96

 FetchType

-0.96

 doInBackground

-0.95

POSITIVE LOGITS

↵↵

0.76

<h3>

0.75

<h2>

0.73

<blockquote>

0.66

</h2>

0.60

↵↵↵

0.58

0.57

[toxicity=0]

0.56

">

0.56

<tr>

0.55

Activations Density 0.048%

white space characters

No Comments

No Known Activations