INDEX

Explanations

references to personal experiences and evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

="@+

-0.66

//

-0.66

 transfieras

-0.65

Portale

-0.64

runApp

-0.64

 rechange

-0.64

]=>

-0.58

ITHUB

-0.58

 snippetHide

-0.57

Kaynakça

-0.57

POSITIVE LOGITS

に関しては

0.52

 soal

0.48

lementation

0.48

 Италијани

0.47

getColumnIndex

0.46

 فقد

0.46

 himo

0.46

Am

0.45

 revanche

0.45

am

0.45

Activations Density 0.223%

references to personal experiences and evaluations

No Comments

No Known Activations