INDEX

Explanations

technical expressions related to coding and debugging

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

DockStyle

-0.80

 oprot

-0.69

StoryboardSegue

-0.68

ReusableCell

-0.64

errHandler

-0.64

complexType

-0.63

 unknownFields

-0.63

Espèce

-0.61

Portail

-0.59

NegativeButton

-0.59

POSITIVE LOGITS

 ***!

0.58

ώρα

0.53

{}/

0.50

évaluateur

0.49

ubourg

0.44

GHIJKLM

0.44

 henne

0.44

 dollari

0.44

newArray

0.43

ότε

0.42

Activations Density 0.058%

technical expressions related to coding and debugging

No Comments

No Known Activations