INDEX

Explanations

representations of lists and list comprehensions in code

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

set notation

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

nezeu

-0.60

StructEnd

-0.57

eqref

-0.54

fromnode

-0.52

 للاسماء

-0.50

ViewImports

-0.50

 endfor

-0.49

Personendaten

-0.49

 forState

-0.48

 eventName

-0.47

POSITIVE LOGITS

SELECT

0.34

 câte

0.34

copy

0.34

 Suom

0.34

rijf

0.34

 Portuguesa

0.34

present

0.33

 tkinter

0.33

function

0.33

Aiheesta

0.32

Activations Density 0.042%

representations of lists and list comprehensions in code

set notation

No Comments

No Known Activations