INDEX

Explanations

the word "then" and variations, indicating sequential connections in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 purpoſe

-0.82

Irm

-0.76

neſs

-0.75

 himſelf

-0.72

 itſelf

-0.70

 ftate

-0.70

ſelf

-0.70

Efq

-0.69

 Carlsbad

-0.69

 feveral

-0.68

POSITIVE LOGITS

 then

3.02

 THEN

2.57

 Then

2.51

then

2.51

Then

2.41

THEN

2.31

 entonces

2.05

 então

1.82

 dann

1.75

 kemudian

1.71

Activations Density 0.089%

the word "then" and variations, indicating sequential connections in the text

No Comments

No Known Activations