INDEX

Explanations

terms related to alignment and layouts in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 <=",

-0.92

Spoljašnje

-0.74

<",

-0.70

JspWriter

-0.68

AccessorTable

-0.67

 Taktlose

-0.65

 bArr

-0.61

 CanadaChoose

-0.60

 tartalomajánló

-0.59

 hefyd

-0.57

POSITIVE LOGITS

Alignment

2.10

 Alignment

1.26

alignment

1.19

 alignment

1.17

 ALIGN

0.89

ALIGN

0.81

 align

0.80

 alignments

0.76

textAlignment

0.73

 aligned

0.72

Activations Density 0.010%

terms related to alignment and layouts in code

No Comments

No Known Activations