INDEX

Explanations

terms related to attributes and assignments in programming.

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

programming syntax related keywords.

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

words related to attending or participating in events, particularly conferences or meetings.

oai_token-act-pair · claude-3-5-sonnet-20240620 Triggered by @bot

following "Att" or "att"

np_acts-logits-general · gemini-2.0-flash

attribute and attributions

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

MemoryWarning

-0.73

jalna

-0.66

AddTagHelper

-0.63

webElementXpaths

-0.63

 latter

-0.60

 requestCode

-0.57

tagext

-0.56

ๆ

-0.55

 Füße

-0.55

Fiona

-0.54

POSITIVE LOGITS

 AttributeSet

0.74

AndEndTag

0.69

 InputDecoration

0.62

).]

0.61

HtmlAttribute

0.60

 Wikidata

0.58

IsContent

0.58

ribut

0.57

Ego

0.56

assertArray