INDEX

Explanations

instances of significant changes or comparisons in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

.*")]

-0.56

 ossia

-0.56

timate

-0.54

-0.51

 covalent

-0.50

+#+

-0.49

 getItemCount

-0.48

arschu

-0.47

 tấn

-0.47

thaler

-0.47

POSITIVE LOGITS

 Administrativna

0.63

 IFTT

0.58

 Paglinawan

0.58

Datuak

0.58

AccessorTable

0.57

 CURIAM

0.53

strophy

0.52

\{\\

0.51

TagMode

0.51

 chng

0.51

Activations Density 0.387%

instances of significant changes or comparisons in various contexts

No Comments

No Known Activations