INDEX

Explanations

instances and discussions of search strategies and keywords in research contexts

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

"search" or "query" terms

np_acts-logits-general · gemini-2.0-flash

search keywords and queries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

MLLoader

-0.68

ReusableCell

-0.63

 GenerationType

-0.63

 <<<<<<<<<<<<<<

-0.59

tinyos

-0.58

 HasFactory

-0.57

buttonShape

-0.56

inWeight

-0.56

TypedDataSet

-0.56

 doInBackground

-0.56

POSITIVE LOGITS

 keywords

0.71

 searches

0.67

 search

0.66

 keyword

0.65

 Keyword

0.60

keywords

0.59

 Search

0.57

 Searches

0.56

keyword

0.56

 Keywords

0.54

Activations Density 0.347%

instances and discussions of search strategies and keywords in research contexts

"search" or "query" terms

search keywords and queries

No Comments

No Known Activations