INDEX

Explanations

evidence and claims related to legal judgments and their implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 majeure

-0.58

 saites

-0.58

Malley

-0.57

PRNewswire

-0.56

 reconn

-0.56

azin

-0.56

URIComponent

-0.55

setopt

-0.54

UVWXYZ

-0.53

évaluateur

-0.53

POSITIVE LOGITS

indicates

0.82

 indicates

0.79

 menunjukkan

0.77

 shows

0.72

 indicate

0.71

 demonstrates

0.69

Shows

0.67

 suggests

0.66

 Shows

0.66

 testifies

0.65

Activations Density 0.531%

evidence and claims related to legal judgments and their implications

No Comments

No Known Activations