INDEX

Explanations

topics related to permissions and documentation in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

ädie

-0.51

interopRequire

-0.51

iseks

-0.49

 serez

-0.48

kheim

-0.45

所に

-0.45

 fizer

-0.44

kens

-0.43

➟

-0.43

 ProtoMessage

-0.43

POSITIVE LOGITS

ThroughAttribute

0.86

 ועל

0.81

 matters

0.78

')['

0.71

是如何

0.70

 topics

0.67

XmlAccessType

0.67

 esternos

0.66

 ogóle

0.65

 topic

0.65

Activations Density 0.618%

topics related to permissions and documentation in various contexts

No Comments

No Known Activations