INDEX

Explanations

phrases that indicate potential outcomes or uncertainties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

ftagPool

-0.57

 voluntary

-0.41

 įsi

-0.39

 CreateTagHelper

-0.38

//

-0.38

 houſe

-0.38

 nearest

-0.38

 immediately

-0.37

 together

-0.35

 directly

-0.35

POSITIVE LOGITS

OGND

0.68

enumi

0.67

possibility

0.66

 synergy

0.63

Informed

0.59

 Informed

0.59

 paranoia

0.56

BagLayout

0.56

Possibility

0.55

 tartalomajánló

0.55

Activations Density 0.265%

phrases that indicate potential outcomes or uncertainties

No Comments

No Known Activations