INDEX

Explanations

names or initials of individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 اطلع

-0.71

 سكانية

-0.71

UnusedPrivate

-0.69

رشف

-0.67

 Beſ

-0.66

 Geste

-0.62

AccessorTable

-0.61

 tartalomajánló

-0.61

expandindo

-0.60

/\.

-0.60

POSITIVE LOGITS

 للمعارف

0.58

RetentionPolicy

0.54

ej

0.50

 GenerationType

0.48

usermodel

0.48

0.46

Co

0.45

HostException

0.45

kva

0.43

DoubleQuotes

0.43

Activations Density 0.126%

names or initials of individuals

No Comments

No Known Activations