INDEX

Explanations

terms and concepts related to legal language and principles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

devamını

-0.73

 betweenstory

-0.69

bbero

-0.64

 pstmt

-0.64

tismo

-0.59

++]=

-0.59

коменду

-0.58

ivamente

-0.58

ionView

-0.58

⎨

-0.58

POSITIVE LOGITS

 enough

0.72

UnsafeEnabled

0.56

PerformLayout

0.55

álló

0.55

ggish

0.52

átní

0.52

 Domes

0.51

ness

0.51

simple

0.51

Dış

0.50

Activations Density 1.060%

terms and concepts related to legal language and principles

No Comments

No Known Activations