INDEX

Explanations

references to computational tasks and item management in a programming context

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

following "that" or "was"

np_acts-logits-general · gemini-2.0-flash

that clauses

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

 useDispatch

-0.67

HtmlAttribute

-0.61

urcht

-0.55

 Larg

-0.55

 wireType

-0.54

SourceChecksum

-0.54

 kaum

-0.53

#+#

-0.53

 intptr

-0.53

 Runs

-0.52

POSITIVE LOGITS

ViewFeatures

0.81

 registered

0.63

 naquele

0.60

曾經

0.60

 وتسجيلات

0.59

 habiendo

0.58

rungsseite

0.58

 geweest

0.57

 flagged

0.56

 previously

0.55

Activations Density 0.824%

references to computational tasks and item management in a programming context

following "that" or "was"

that clauses

No Comments

No Known Activations