INDEX

Explanations

terms related to nursing and engineering

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

CppCodeGen

-0.75

gnition

-0.71

tų

-0.67

Geplaatst

-0.67

 florales

-0.66

 aidant

-0.65

^(@)

-0.64

almaz

-0.64

 perſon

-0.63

LLocation

-0.63

POSITIVE LOGITS

 protoimpl

0.76

 Insee

0.66

maid

0.65

 الوطنيه

0.56

('''

0.54

Boas

0.52

 برانيه

0.52

<<-

0.51

 pylori

0.51

émoc

0.50

Activations Density 0.143%

terms related to nursing and engineering

No Comments

No Known Activations