INDEX

Explanations

references to the term "Har" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

])));

-0.54

medriver

-0.53

 Cowper

-0.53

 mergeFrom

-0.53

EDEFAULT

-0.52

 sumpay

-0.52

 يتيمه

-0.51

 članak

-0.51

abestanden

-0.50

 приш

-0.50

POSITIVE LOGITS

 المعيارى

0.58

GEBURTSDATUM

0.57

InputBorder

0.57

 الرياضيه

0.57

StoryboardSegue

0.55

 Harrell

0.54

URLException

0.52

Har

0.52

Har

0.51

 BorderRadius

0.51

Activations Density 0.135%

references to the term "Har" in various contexts

No Comments

No Known Activations