INDEX

Explanations

references to entities within a framework context

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

isSuccessful

-0.88

 Fros

-0.84

<<-

-0.83

ffron

-0.81

 sunshine

-0.81

JAS

-0.81

AppRoutingModule

-0.81

__(/*!

-0.80

termilk

-0.80

 Koen

-0.80

POSITIVE LOGITS

 entity

2.46

entity

2.29

 Entity

2.27

 entities

2.23

 Entities

2.19

entities

2.15

Entity

2.09

ENTITY

2.03

 ENTITY

2.02

Entities

1.96

Activations Density 0.071%

references to entities within a framework context

No Comments

No Known Activations