INDEX

Explanations

mathematical notations or expressions related to complex equations and models

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

_(

-0.78

!(

-0.70

!(

-0.67

.(

-0.65

-(

-0.64

__(

-0.64

<eos>

-0.64

-0.63

 Sander

-0.62

POSITIVE LOGITS

leſs

1.10

 myſelf

1.04

$_"

1.00

 itſelf

1.00

‴

0.99

ſelves

0.99

 himſelf

0.98

$[-

0.97

Portale

0.96

ſelf

0.92

Activations Density 0.380%

mathematical notations or expressions related to complex equations and models

No Comments

No Known Activations