INDEX

Explanations

negative contractions and expressions of disbelief or denial

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.40.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

InInspector

-0.61

 Schenk

-0.59

Споља

-0.58

 Barbier

-0.58

 dimenti

-0.58

 Fras

-0.57

SourceChecksum

-0.57

 indepen

-0.57

 Mazz

-0.57

 Cartwright

-0.57

POSITIVE LOGITS

'"

0.48

’?

0.47

'...

0.46

0.45

̵

0.44

’’

0.43

'`

0.43

Õ

0.43

'".

0.43

ʼ

0.43

Activations Density 0.108%

negative contractions and expressions of disbelief or denial

No Comments

No Known Activations

negative contractions and expressions of disbelief or denial

No Comments

No Known Activations