INDEX

Explanations

terms related to legal or political contexts, particularly those involving manipulation and control

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Catarina

-0.56

 McKinney

-0.55

Lorenzo

-0.54

thood

-0.53

IOR

-0.52

 Jozef

-0.51

]='\

-0.51

 Rump

-0.50

Dö

-0.50

片

-0.49

POSITIVE LOGITS

0.93

ⓘ

0.87

 Roskov

0.82

脚注の使い方

0.81

 asupra

0.75

Geplaatst

0.75

ValueStyle

0.74

fjspx

0.73

AntiForgeryToken

0.71

mybatisplus

0.71

Activations Density 3.100%

terms related to legal or political contexts, particularly those involving manipulation and control

No Comments

No Known Activations