INDEX

Explanations

repeated phrases or concepts indicating sameness or consistency across different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132

Prompts (Dashboard)

24,576 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

webElementGuid

-0.41

initComponents

-0.39

XMLSchema

-0.39

ClientSize

-0.39

XmlType

-0.39

WriteTagHelper

-0.37

RTEX

-0.36

queryInterface

-0.36

mybatisplus

-0.36

verwijspagina

-0.35

POSITIVE LOGITS

 same

1.30

Same

1.24

same

1.23

 Same

1.15

 dieselben

1.09

 gleichen

1.05

 SAME

1.04

 denselben

1.03

 dieselbe

1.03

 derselbe

1.02

Activations Density 0.591%

repeated phrases or concepts indicating sameness or consistency across different contexts

No Comments

No Known Activations