INDEX

Explanations

references to legal judgments and verdicts

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

vaz

-0.58

 useRef

-0.58

WriteTagHelper

-0.57

anasia

-0.56

mie

-0.56

SourceChecksum

-0.56

 AssemblyProduct

-0.55

tem

-0.55

var

-0.54

burgo

-0.53

POSITIVE LOGITS

 judgment

0.96

 judgement

0.95

 judgments

0.84

judgment

0.84

socket

0.73

 judgements

0.72

 Judgment

0.70

 Judgement

0.69

 verdict

0.67

 judged

0.64

Activations Density 0.092%

references to legal judgments and verdicts

No Comments

No Known Activations