INDEX

Explanations

verbs that express command or caution

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

OGND

-0.69

 pylint

-0.66

requestData

-0.62

subsubsection

-0.61

pisah

-0.61

herself

-0.58

pira

-0.57

hingga

-0.57

gheny

-0.56

řel

-0.56

POSITIVE LOGITS

 Donny

0.93

Dont

0.83

Doy

0.80

TagHelper

0.76

 Dont

0.76

dont

0.75

 Jangan

0.74

 beware

0.73

勿

0.72

Don

0.72

Activations Density 0.069%

verbs that express command or caution

No Comments

No Known Activations