INDEX

Explanations

phrases expressing uncertainty or conditions related to problems and limitations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

reszcie

-0.56

 '\\;'

-0.49

Mutagenicity

-0.48

кновен

-0.48

mulos

-0.48

 يتيمه

-0.47

 autorytatywna

-0.46

SpringBootTest

-0.46

 HasFactory

-0.45

LOYEES

-0.45

POSITIVE LOGITS

ScopeManager

0.75

initComponents

0.67

 harm

0.62

 meaningfully

0.62

 objection

0.62

 greatly

0.61

offsetWidth

0.59

 trenger

0.58

 особы

0.58

TagMode

0.58

Activations Density 0.278%

phrases expressing uncertainty or conditions related to problems and limitations

No Comments

No Known Activations