INDEX

Explanations

negations and the verb "have" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 Eunice

-0.72

 صوتيه

-0.72

 Draws

-0.71

riwal

-0.71

➢

-0.70

 menuItem

-0.69

 Polyp

-0.68

Hochspringen

-0.68

 itemList

-0.68

GNP

-0.68

POSITIVE LOGITS

 been

0.85

<thead>

0.75

 LCCN

0.72

pshots

0.71

 Haven

0.69

最快更新

0.69

Inflater

0.68

않

0.66

ineno

0.66

 recently

0.65

Activations Density 0.087%

negations and the verb "have" in various contexts

No Comments

No Known Activations