INDEX

Explanations

references to the term "Ind" or variations thereof

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

InlineData

-0.65

кономі

-0.58

 CanadaChoose

-0.57

StandardCharsets

-0.55

ParallelGroup

-0.54

readystatechange

-0.52

reportWebVitals

-0.52

expiresIn

-0.52

 inégal

-0.49

↵↵

-0.49

POSITIVE LOGITS

 للمعارف

0.90

ⓧ

0.75

chens

0.68

Ind

0.68

$_"

0.67

<<=

0.66

 Defence

0.66

leg

0.66

^(@)

0.63

ẞ

0.63

Activations Density 0.116%

references to the term "Ind" or variations thereof

No Comments

No Known Activations