INDEX

Explanations

commands and actions related to setting variables or parameters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

Efq

-0.89

 Jefus

-0.87

 myſelf

-0.84

 itſelf

-0.84

ſelves

-0.83

 Theſe

-0.79

 becauſe

-0.78

ſelf

-0.76

 themſelves

-0.75

 houſe

-0.74

POSITIVE LOGITS

Then

0.61

 Then

0.59

 THEN

0.56

 then

0.53

 anschließend

0.50

then

0.50

 trasform

0.50

poi

0.49

ammen

0.49

 vervolgens

0.48

Activations Density 0.543%

commands and actions related to setting variables or parameters

No Comments

No Known Activations