INDEX

Explanations

mathematical expressions and notations, particularly involving variables and functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 препратки

-0.82



-0.79

 beginnetje

-0.69

 Theſe

-0.68

parsedMessage

-0.65

 bezeichneter

-0.64

WebVitals

-0.63

 surla

-0.61

 purpoſe

-0.60

 myſelf

-0.60

POSITIVE LOGITS

參考文獻

0.65

 best

0.55

 meubles

0.49

Източници

0.48

แทน

0.48

 sama

0.46

STERY

0.45

avares

0.45

re

0.45

Activations Density 5.291%

mathematical expressions and notations, particularly involving variables and functions

No Comments

No Known Activations