INDEX

Explanations

terms related to scientific publications or academic journals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

-0.52

you

-0.51

-0.50

-0.49

<strong>

-0.49

is

-0.46

POSITIVE LOGITS

 betweenstory

0.98

StoryboardSegue

0.95

ChildScrollView

0.95

 '\\;'

0.95

RenderAtEndOf

0.94

ագրություններ

0.94

ViewImports

0.93

 stället

0.89

 EconPapers

0.89

mybatisplus

0.89

Activations Density 0.573%

terms related to scientific publications or academic journals

No Comments

No Known Activations