INDEX

Explanations

references to children or kids

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

LabelTagHelper

-0.65

ghen

-0.60

 Vertra

-0.58

Antecedentes

-0.58

InteropServices

-0.56

batore

-0.56

mathscr

-0.55

 odkazy

-0.54

 Hara

-0.54

inale

-0.54

POSITIVE LOGITS

 kids

3.76

 Kids

3.31

Kids

3.24

kids

3.21

kid

3.06

 KIDS

3.03

KIDS

2.54

Kid

2.38

Kid

2.36

KID

2.34

Activations Density 0.057%

references to children or kids

No Comments

No Known Activations