INDEX

Explanations

words related to safety and reliability in services or products

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

del

-0.62

-0.58

de

-0.55

qu

-0.53

 Corp

-0.52

ter

-0.50

le

-0.50

 half

-0.49

him

-0.49

min

-0.49

POSITIVE LOGITS

Personendaten

1.25

+#+#

1.21

interopRequire

1.01

 CreateTagHelper

1.01

 ExecuteAsync

0.94

IntoConstraints

0.92

 AssemblyTitle

0.91

EndGlobalSection

0.91

 AssemblyProduct

0.90

ConstraintMaker

0.89

Activations Density 0.107%

words related to safety and reliability in services or products

No Comments

No Known Activations