INDEX

Explanations

details related to legal charges and convictions

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

ModelForm

-0.52

mentable

-0.50

mybatisplus

-0.48

ciller

-0.47

TagMode

-0.47

 stij

-0.47

nende

-0.46

CAB

-0.46

sedown

-0.46

growing

-0.46

POSITIVE LOGITS

 allegedly

0.78

 suspected

0.71

 acusado

0.69

 accused

0.69

 diduga

0.68

 alleged

0.67

expandindo

0.66

StoryboardSegue

0.64

 confessed

0.63

 NSCoder

0.62

Activations Density 0.375%

details related to legal charges and convictions

No Comments

No Known Activations