INDEX

Explanations

code-related syntax or structures, particularly in programming contexts

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

Code, identifiers, or programming terms

np_acts-logits-general · gemini-2.0-flash

list indexing and slicing

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

исленность

-0.57

-0.56

ρες

-0.51

 Nine

-0.50

 grund

-0.49

 estekak

-0.47

 bâton

-0.46

indor

-0.46

 giriş

-0.46

POSITIVE LOGITS

клопе

0.69

WriteBarrier

0.67

0.60

 ligiloj

0.60

SequentialGroup

0.58

 ListNode

0.58

 five

0.56

ViewFeatures

0.56

Fif

0.54

Activations Density 0.033%

code-related syntax or structures, particularly in programming contexts

Code, identifiers, or programming terms

list indexing and slicing

No Comments

No Known Activations