INDEX

Explanations

terms related to legal judgments and courtroom decisions

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

antic

-0.61

ծ

-0.56

ixin

-0.56

herz

-0.53

Parcelize

-0.53

 ماس

-0.53

vų

-0.52

흡

-0.52

PERT

-0.51

POSITIVE LOGITS

 judgment

2.31

 judgement

2.20

 Judgment

2.13

judgment

2.13

 judgments

2.11

 Judgement

2.10

 judgements

2.01

Judgment

1.94

 JUDGMENT

1.86

jud

1.77

Activations Density 0.277%

terms related to legal judgments and courtroom decisions

No Comments

No Known Activations