INDEX

Explanations

instances of titles, roles, or descriptors of people

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

 للاسماء

-0.58

mogat

-0.46

 hiszen

-0.45

windowFixed

-0.44

capace

-0.43

 témoin

-0.42

 piaggio

-0.42

seguida

-0.41

reciate

-0.41

reciated

-0.41

POSITIVE LOGITS

forKey

0.75

httphttps

0.73

новништво

0.73

 senior

0.68

NUMX

0.67

+#+

0.66

TagHelpers

0.65

AddHtmlAttribute

0.65

urcht

0.65

 middleware

0.64

Activations Density 0.118%

instances of titles, roles, or descriptors of people

No Comments

No Known Activations