INDEX

Explanations

phrases related to providing information or guidance about procedures

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

 HasFactory

-0.59

tonode

-0.57

hastly

-0.57

quelize

-0.57

fjspx

-0.55

 Catawiki

-0.55

日閲覧

-0.55

ьаж

-0.55

 Townsend

-0.53

 objectForKey

-0.53

POSITIVE LOGITS

enumi

0.47

 يتيمه

0.46

OGND

0.46

 AssemblyCompany

0.44

انجليز

0.44

 Normdatei

0.44

initComponents

0.43

semantics

0.43

<?

0.42

ectoria

0.42

Activations Density 0.058%

phrases related to providing information or guidance about procedures

No Comments

No Known Activations