INDEX

Explanations

symbols or characters used for formatting or structuring text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

↵

-0.61

-0.52

to

-0.51

loroethene

-0.51

-0.48

 when

-0.47

≦)

-0.47

webElementXpaths

-0.47

POSITIVE LOGITS

 ujednoznacz

0.90

EnableWeb

0.89

ſelf

0.86

tvguidetime

0.86

ſelves

0.85

 Reſ

0.85

enumi

0.85

 Beſ

0.84

^(@)

0.83

 StatefulWidget

0.82

Activations Density 0.007%

symbols or characters used for formatting or structuring text

No Comments

No Known Activations