INDEX

Explanations

references to APIs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

DeleteBehavior

-0.69

脚注の使い方

-0.68

ecutable

-0.67

تحميل

-0.67

Бахар

-0.67

 colouring

-0.65

Portale

-0.64

 disponibilités

-0.63

 Catawiki

-0.63

UnknownFieldSet

-0.60

POSITIVE LOGITS

API

1.21

api

1.14

 endpoint

1.01

Api

0.98

Endpoint

0.95

endpoint

0.91

 APIs

0.88

 Endpoint

0.88

api

0.77

API

0.74

Activations Density 0.070%

references to APIs

No Comments

No Known Activations