INDEX

Explanations

programming constructs related to conditional statements and returning boolean values

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

code snippets and programming context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

MessageOf

-0.47

 informée

-0.41

BitConverter

-0.40



-0.38

 protoimpl

-0.37

={({

-0.37

方

-0.37

}{*}{

-0.37

届

-0.36

 outside

-0.36

POSITIVE LOGITS

Personendaten

0.66

iastes

0.56

RefNanny

0.53

 sprüche

0.50

IndentedString

0.48

 amizade

0.47

peq

0.47

 myſelf

0.47

 Comprometido

0.47

rungsseite

0.46

Activations Density 0.001%

programming constructs related to conditional statements and returning boolean values

code snippets and programming context

No Comments

No Known Activations