INDEX

Explanations

special markers or tokens that denote the beginning of sections or paragraphs in textual data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 насељу

-0.64

olum

-0.52

 Life

-0.50

 part

-0.50

 life

-0.49

den

-0.49

PrimaryKey

-0.48

 Part

-0.48

Sh

-0.48

“

-0.48

POSITIVE LOGITS

 itſelf

0.85

 تضيفلها

0.78

 pleaſure

0.78

 uſed

0.76

 myſelf

0.76

 faſt

0.76

 ſch

0.69

ſelf

0.69

 becauſe

0.65

Mep

0.65

Activations Density 0.046%

special markers or tokens that denote the beginning of sections or paragraphs in textual data

No Comments

No Known Activations