INDEX

Explanations

phrases indicating a high probability or likelihood of something occurring

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

帖最后由

-0.55

 BoxFit

-0.54

RunWith

-0.49

oredCriteria

-0.49

IntoConstraints

-0.49

grunns

-0.48

 alluminio

-0.47

MatInputModule

-0.47

 BoxDecoration

-0.47

rrggbb

-0.47

POSITIVE LOGITS

 likely

4.09

likely

3.72

 Likely

3.63

Likely

3.50

 probable

2.20

 likelihood

2.05

 unlikely

1.99

LIK

1.91

probable

1.91

 Probable

1.89

Activations Density 0.088%

phrases indicating a high probability or likelihood of something occurring

No Comments

No Known Activations