INDEX

Explanations

technical terms and variables in programming and computational contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

writeFieldEnd

-0.56

 bicchiere

-0.51

ToListAsync

-0.49

'{@

-0.49

échal

-0.47

 parseFrom

-0.47

OfYear

-0.45

 plagioclase

-0.45

 titoli

-0.45

thias

-0.45

POSITIVE LOGITS

 autorytatywna

0.68

rrggbb

0.66

ExtendWith

0.65

0.62

 ujednoznacz

0.59

WarningLevel

0.56

principalColumn

0.56

 gynhyrchwyd

0.56

وحة

0.55

astify

0.54

Activations Density 1.766%

technical terms and variables in programming and computational contexts

No Comments

No Known Activations