INDEX

Explanations

negative sentiments or allegations against people or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

Espèce

-0.66

 HasFactory

-0.63

 uitzicht

-0.59

Filmographie

-0.57

geführten

-0.57

INSTALLED

-0.56

URLException

-0.55

awsze

-0.55

Filmografie

-0.55

 käyttää

-0.54

POSITIVE LOGITS

SequentialGroup

0.84

 Twitter

0.78

 posts

0.76

 twitter

0.75

 tweets

0.73

 tweeted

0.72

 tweet

0.70

Twitter

0.67

 tweeting

0.67

 viral

0.66

Activations Density 0.147%

negative sentiments or allegations against people or entities

No Comments

No Known Activations