INDEX

Explanations

references to technology products and their features

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

 vardır

-0.54

是我的

-0.43

私は

-0.42

="{{$

-0.42

my

-0.41

 xxxx

-0.40

MPI

-0.40

 мои

-0.40

 pedagogy

-0.39

私に

-0.39

POSITIVE LOGITS

setVerticalGroup

0.99

 presumably

0.92

expandindo

0.91

presumably

0.91

 Presumably

0.89

 rumoured

0.87

 rumored

0.86

脚注の使い方

0.84

تقاوى

0.83

complexContent

0.82

Activations Density 0.202%

references to technology products and their features

No Comments

No Known Activations

references to technology products and their features

No Comments

No Known Activations