INDEX

Explanations

references to client-related terms and identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 écou

-0.71

RoutingModule

-0.70

 élector

-0.69

Amos

-0.69

 CreateTagHelper

-0.69

 regardé

-0.68

umato

-0.67

loom

-0.67

 Spur

-0.67

 FLAGS

-0.66

POSITIVE LOGITS

 clients

1.53

 Clients

1.45

clients

1.35

 getClient

1.32

 CLIENT

1.31

 Client

1.31

Client

1.31

 client

1.30

Clients

1.29

client

1.18

Activations Density 0.043%

references to client-related terms and identifiers

No Comments

No Known Activations