INDEX

Explanations

numerical data or values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

an

-0.56

itesi

-0.51

Ư

-0.50

<eos>

-0.49

:+:

-0.49

bajo

-0.49

AddWithValue

-0.48

med

-0.48

AutoField

-0.47

UpInside

-0.46

POSITIVE LOGITS

 pleaſure

0.87

 juſ

0.87

 ſche

0.80

 houſe

0.78

 reaſon

0.78

 ſte

0.77

 ſta

0.75

 ſou

0.75

uſ

0.74

 viſ

0.73

Activations Density 0.980%

numerical data or values

No Comments

No Known Activations