INDEX

Explanations

repeated instances of the word "hi."

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

 actionTypes

-0.71

 Domini

-0.60

 Autorizaciones

-0.59

rifuge

-0.58

 Alam

-0.56

Referencies

-0.56

βάλ

-0.56

醐

-0.56

kloped

-0.56

atoire

-0.55

POSITIVE LOGITS

hi

4.09

HI

2.82

hi

2.75

Hi

2.75

Hi

2.68

HI

2.25

hiy

1.74

hii

1.59

hiya

1.37

hie

1.35

Activations Density 0.114%

repeated instances of the word "hi."

No Comments

No Known Activations