INDEX

Explanations

terms related to masks used in various contexts, particularly in technology and policy discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/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.17.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

 AssemblyTitle

-0.78

 EconPapers

-0.73

:✨

-0.73

полнитель

-0.73

✨:

-0.71



-0.71

 Eura

-0.70

 découver

-0.70

+#+#

-0.69

Життєпис

-0.68

POSITIVE LOGITS

 mask

0.72

 masks

0.69

 MASK

0.68

Masks

0.68

mask

0.68

 Mask

0.68

 маска

0.67

ers

0.66

MASK

0.65

 ""),

0.64

Activations Density 0.299%

terms related to masks used in various contexts, particularly in technology and policy discussions

No Comments

No Known Activations