INDEX

Explanations

mathematical formatting and notation related to coordinates and alignment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 CreateTagHelper

-0.72

 Bere

-0.67

bek

-0.63

AutoScaleMode

-0.63

PLE

-0.62

∽

-0.61

discussed

-0.61

 userSchema

-0.60

IES

-0.59

isp

-0.59

POSITIVE LOGITS

quad

2.26

 quad

1.35

 quadrant

1.29

Quad

1.27

 quads

1.26

 Quad

1.23

QUAD

1.13

qquad

1.05

 تانيه

1.03

 Quadrant

0.96

Activations Density 0.088%

mathematical formatting and notation related to coordinates and alignment

No Comments

No Known Activations