INDEX

Explanations

references to legal terms and decisions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

principalTable

-0.64

IsContent

-0.62

◆◆

-0.55

 herbe

-0.54

SPATH

-0.54

inici

-0.51

ális

-0.51

abri

-0.50

новниш

-0.49

utilisons

-0.49

POSITIVE LOGITS

expandindo

0.93

 CURIAM

0.81

ว่า

0.68

 يتيمه

0.66

__':

0.63

かわらず

0.61

 ujednoznacz

0.60

 pinulongan

0.59

 rằng

0.59

__':

0.59

Activations Density 0.502%

references to legal terms and decisions

No Comments

No Known Activations

references to legal terms and decisions

No Comments

No Known Activations