INDEX

Explanations

programming operators and delimiters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 ویکی‌پدی

-0.82

 nakalista

-0.79

 Савезне

-0.78

 समीक्षाओं

-0.76

RTEX

-0.75

 незавершена

-0.75

 lenker

-0.74

 linkovi

-0.73

 Infórmanos

-0.71

 мәкал

-0.70

POSITIVE LOGITS

0.89

0.62

0.55

0.52

0.48

my

0.47

io

0.47

findViewById

0.46

Activations Density 0.320%

programming operators and delimiters

No Comments

No Known Activations