INDEX

Explanations

references to specific studies and their results

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

ilibr

-0.47

ServiceClient

-0.43

litch

-0.43

Население

-0.41

prit

-0.40

 smtplib

-0.39

 Lycée

-0.38

 Safran

-0.38

Provider

-0.38

μβρίου

-0.38

POSITIVE LOGITS

AddTagHelper

1.00

Personensuche

0.98

 للاسماء

0.75

Efq

0.74

webElementXpaths

0.74

SequentialGroup

0.73

ValueStyle

0.72

expandindo

0.71

 الرياضيه

0.71

########.

0.70

Activations Density 0.619%

references to specific studies and their results

No Comments

No Known Activations