INDEX

Explanations

terms related to allegations and claims made about actions or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

ReusableCell

-0.60

-0.59

 समीक्षक

-0.57

-0.55

pixabay

-0.54

 esterni

-0.52

-0.48

 apart

-0.48

-0.47

teamId

-0.47

POSITIVE LOGITS

 alleged

1.32

 perceived

1.11

 purported

1.09

 projected

1.08

 Perceived

1.03

 supposed

1.02

 advertised

1.02

Reported

0.99

 Projected

0.99

 planned

0.99

Activations Density 0.386%

terms related to allegations and claims made about actions or events

No Comments

No Known Activations