INDEX

Explanations

phrases indicating the significance or impact of subjects within various contexts

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

Follows punctuation marks

np_acts-logits-general · gemini-2.0-flash

beginning of sentences

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

:✨

-0.68

setVerticalGroup

-0.60



-0.53

 AssemblyCulture

-0.50

 հղումներ

-0.50

kháu

-0.48

 detailsLots

-0.47

SharedCtor

-0.47

 autorytatywna

-0.47

RenderAtEndOf

-0.46

POSITIVE LOGITS

MigrationBuilder

0.42

Clik

0.40

DebuggerNonUser

0.39

dro

0.37

setTag

0.36

 drops

0.35

 reader

0.35

ogn

0.34

LabelTagHelper

0.34

 smiles

0.33

Activations Density 1.090%

phrases indicating the significance or impact of subjects within various contexts

Follows punctuation marks

beginning of sentences

No Comments

No Known Activations