INDEX

Explanations

technical terms related to programming and code imports

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

#+#

-0.80

ReusableCell

-0.80

Chham

-0.79

RegistryLite

-0.77

 nakalista

-0.76

featureID

-0.75

RuleContext

-0.72

ArgsConstructor

-0.72

 iprot

-0.71

Дереккөздер

-0.69

POSITIVE LOGITS

df

0.46

Hau

0.46

 folle

0.45

felde

0.44

chier

0.42

 CURIAM

0.42

aure

0.41

ese

0.41

http

0.41

langer

0.40

Activations Density 0.035%

technical terms related to programming and code imports

No Comments

No Known Activations