INDEX

Explanations

references to specific programming functions or methods along with associated parameters

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

EDEFAULT

-0.50

SequentialGroup

-0.46

@[+][

-0.43

MeasureSpec

-0.39

TestingModule

-0.38

 StringTokenizer

-0.37

 könig

-0.35

MessageTagHelper

-0.35

 pinggang

-0.34

awtextra

-0.34

POSITIVE LOGITS

 виправивши

0.64

adaptiveStyles

0.55

FV

0.54

 noDo

0.53

Gro

0.52

MessageOf

0.50

 solution

0.48

⤹

0.48

lösung

0.48

 Morn

0.47

Activations Density 0.100%

references to specific programming functions or methods along with associated parameters

No Comments

No Known Activations