INDEX

Explanations

legal and procedural terms related to investigations and assessments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 виправивши

-0.72

KURZBESCHREIBUNG

-0.69

rungsseite

-0.68

!')

-0.67

€¦

-0.64

FunctionFlags

-0.63

SuspendLayout

-0.63

SPATH

-0.61

WebVitals

-0.61

enumi

-0.60

POSITIVE LOGITS

“

2.86

2.79

 “[

2.08

 “…

2.06

«

1.98

「

1.98

"[

1.97

 "...

1.95

„

1.92

 “...

1.89

Activations Density 2.110%

legal and procedural terms related to investigations and assessments

No Comments

No Known Activations