INDEX

Explanations

iterations or loops in code

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

Loops, specifically the "for" keyword

np_acts-logits-general · gemini-2.0-flash

for loops

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

SME

-0.44

łas

-0.44

Contexto

-0.43

临

-0.41

畢

-0.41

awsze

-0.41

SHR

-0.41

vän

-0.40

ARGS

-0.40

 लग

-0.39

POSITIVE LOGITS

Personendaten

1.09

 дописавши

1.08

IUrlHelper

1.05

fjspx

1.04

Geplaatst

0.97

AddTagHelper

0.96

DeleteBehavior

0.94

SourceChecksum

0.93

FunctionFlags

0.90

enumii

0.88

Activations Density 0.025%

iterations or loops in code

Loops, specifically the "for" keyword

for loops

No Comments

No Known Activations