INDEX

Explanations

text that discusses categorization or classification

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

solid

-0.54

 solid

-0.54

 Solid

-0.54

Solid

-0.51

APIView

-0.51

owal

-0.51

 soli

-0.47

 SOLID

-0.46

onesome

-0.45

شاهد

-0.45

POSITIVE LOGITS

 divided

0.95

 initComponents

0.89

 subdivided

0.89

 Divided

0.89

 divides

0.88

divided

0.86

 autorytatywna

0.86

分成

0.85

 partitioned

0.85

 subdiv

0.82

Activations Density 0.244%

text that discusses categorization or classification

No Comments

No Known Activations