INDEX

Explanations

terms related to accuracy and precision in measurements or descriptions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Réponses

-0.69

-0.67

pj

-0.64

 nakalista

-0.62

olutamente

-0.61

enswert

-0.60

 frutti

-0.59

 componente

-0.58

 Schuster

-0.58

findpost

-0.58

POSITIVE LOGITS

 Exact

2.03

 exact

1.98

Exact

1.90

exact

1.81

 EXACT

1.68

 exacte

1.38

 exacta

1.37

EXACT

1.31

 exacto

1.28

 precise

1.21

Activations Density 0.091%

terms related to accuracy and precision in measurements or descriptions

No Comments

No Known Activations