INDEX

Explanations

terms related to accusations and allegations of misconduct

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 viewDidLoad

-0.69

ContentAsync

-0.67

 بيها

-0.67

utnik

-0.65

Portail

-0.65

 Paglinawan

-0.61

 home

-0.61

ležité

-0.60

OGND

-0.60

panou

-0.59

POSITIVE LOGITS

 allege

1.38

 alleges

1.34

 suspected

1.18

 alleging

1.16

 alleged

1.16

 allegations

1.13

 accuse

1.07

 allegation

1.05

Alleg

1.05

 accuses

1.04

Activations Density 0.201%

terms related to accusations and allegations of misconduct

No Comments

No Known Activations