INDEX

Explanations

instances of time-related phrases or words indicating specific conditions or settings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 zamanda

-0.58

şem

-0.58

 your

-0.56

jant

-0.56

 dataSnapshot

-0.55

strtolower

-0.52

برت

-0.52

 NSCoder

-0.52

our

-0.51

φορά

-0.49

POSITIVE LOGITS

tvguidetime

0.73

 صوتيه

0.70

SOUNDBITE

0.68

DeleteBehavior

0.67

 Himo

0.64

extAlignment

0.57

SourceChecksum

0.56

Referències

0.55

 يتيمه

0.55

ᅠ

0.54

Activations Density 0.362%

instances of time-related phrases or words indicating specific conditions or settings

No Comments

No Known Activations