INDEX

Explanations

mentions of the name "Jack" or "Jackson."

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

 Petal

-0.72

 Bettina

-0.68

 petal

-0.65

 Cristiano

-0.65

DebuggerNonUser

-0.60

NOPQRST

-0.60

PhysRev

-0.59

 réf

-0.59

CBT

-0.55

Cristiano

-0.53

POSITIVE LOGITS

 Jack

4.41

Jack

4.20

 jack

3.94

jack

3.70

 JACK

3.54

JACK

3.18

 jacks

2.80

 Jacks

2.80

jacks

2.67

ジャック

2.22

Activations Density 0.168%

mentions of the name "Jack" or "Jackson."

No Comments

No Known Activations