INDEX

Explanations

phrases that provide information about individuals and their actions or roles

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

<bos>

-0.71

 potenciales

-0.59

 wikipagina

-0.59

Пото

-0.58



-0.58

 echte

-0.55

cocc

-0.55

 temporales

-0.54

 potřeb

-0.54

 végétale

-0.53

POSITIVE LOGITS

BeginContext

0.86

enumi

0.85

 AppBar

0.70

TargetException

0.67

IBOutlet

0.62

 geldig

0.61

RunWith

0.61

enumii

0.60

íncia

0.58

 whom

0.58

Activations Density 0.197%

phrases that provide information about individuals and their actions or roles

No Comments

No Known Activations