INDEX

Explanations

references to context and background information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 sexuales

-0.65

 laiton

-0.60

 rechange

-0.58

 équilibr

-0.58

 satisfe

-0.57

 leaſt

-0.54

 dignité

-0.54

 GenerationType

-0.53

hematical

-0.53

 astuces

-0.53

POSITIVE LOGITS

 context

1.26

 backdrop

1.20

 contexts

1.14

 contesto

1.12

 contexto

1.08

 environment

1.04

 contexte

1.00

 contextos

0.99

context

0.99

 CONTEXT

0.96

Activations Density 0.358%

references to context and background information

No Comments

No Known Activations