INDEX

Explanations

terms associated with legal proceedings and court rulings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

#+#

-0.89

thâu

-0.82

rungsseite

-0.81

Personendaten

-0.80

COLN

-0.80

లాలు

-0.77

 BoxFit

-0.77

ScopeManager

-0.75

 bezeichneter

-0.75

AutoresizingMask

-0.74

POSITIVE LOGITS

 says

0.76

 recalls

0.71

 describes

0.67

 hindsight

0.67

 retrospect

0.64

 recounts

0.63

當時

0.62

 alleges

0.62

 Describes

0.61

 describe

0.60

Activations Density 0.530%

terms associated with legal proceedings and court rulings

No Comments

No Known Activations