INDEX

Explanations

concepts related to system functionality and application

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 Италијани

-0.72

 Societies

-0.72

 myſelf

-0.70

 themſelves

-0.68

 reaſon

-0.68

ưỡi

-0.67

ensuche

-0.66

 quæ

-0.65

 Presses

-0.64

 Bookstore

-0.64

POSITIVE LOGITS

0.45

 sheet

0.44

chafft

0.42

 sesso

0.42

TagMode

0.42

Está

0.41

 esat

0.40

gså

0.40

之一

0.39

afone

0.38

Activations Density 1.030%

concepts related to system functionality and application

No Comments

No Known Activations