INDEX

Explanations

technical terms related to programming, mathematics, or software features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

TintMode

-0.93

 Roskov

-0.83

 resourceCulture

-0.73

 disambiguazione

-0.72

scriptcase

-0.71

WithIOException

-0.70

(!__

-0.70

 Мексичка

-0.67

 ProtoMessage

-0.66

WriteTagHelper

-0.66

POSITIVE LOGITS

 including

0.49

 functions

0.47

 parts

0.47

包括

0.46

 stuff

0.45

 items

0.45

 features

0.43

務

0.43

lagen

0.41

 tờ

0.41

Activations Density 0.949%

technical terms related to programming, mathematics, or software features

No Comments

No Known Activations