INDEX

Explanations

terms related to the concept of identification, particularly in scientific or analytical contexts

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

The letter "f" followed by other characters

np_acts-logits-general · gemini-2.0-flash

fi

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 виправивши

-0.51

 صوتيه

-0.51

tractor

-0.50

Referanser

-0.47

jspx

-0.45

awtextra

-0.44

dera

-0.44

reactivex

-0.43

ksikon

-0.43

bin

-0.42

POSITIVE LOGITS

RenderAtEndOf

0.66

 fign

0.65

 itſelf

0.65

 tfsi

0.65

 pngtree

0.64

 Logement

0.64

 Femen

0.63

 perfons

0.61

ﬁ

0.60

ificance

0.60

Activations Density 0.271%

terms related to the concept of identification, particularly in scientific or analytical contexts

The letter "f" followed by other characters

fi

No Comments

No Known Activations