INDEX

Explanations

questions and prompts for engagement or action

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

]--;

-0.93

StandardCharsets

-0.70

staticmethod

-0.70

crollView

-0.67

GEBURTSDATUM

-0.66

AccessorTable

-0.65

#+#

-0.64

pulumi

-0.63

";}

-0.62

RuleContext

-0.62

POSITIVE LOGITS

わけです

0.43

 Packed

0.43

 kinematics

0.43

Mounted

0.43

mark

0.42

offer

0.41

感的

0.41

 acto

0.41

そんな

0.40

tive

0.40

Activations Density 0.146%

questions and prompts for engagement or action

No Comments

No Known Activations