INDEX

Explanations

scientific citations and references

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

NUMX

-0.78

 itſelf

-0.77

 leaſt

-0.76

ſelf

-0.72

 kaynağından

-0.72

ſelves

-0.71

stateProvider

-0.70

leſs

-0.70

^(@)

-0.70

Efq

-0.70

POSITIVE LOGITS

 متعلقه

0.58

########.

0.57

enumi

0.52

umumkan

0.50

<bos>

0.48

 thuật

0.44

XmlAccessType

0.42

 aumentando

0.41

esModule

0.40

 recentemente

0.40

Activations Density 0.230%

scientific citations and references

No Comments

No Known Activations