INDEX

Explanations

programming-related keywords and annotations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 enged

-0.59

AutoScaleMode

-0.58

æng

-0.50

Према

-0.49

 оригіналу

-0.48

 matahari

-0.47

 marchandises

-0.46

NegativeButton

-0.45

fæ

-0.45

 démocr

-0.44

POSITIVE LOGITS

 betweenstory

0.88

RTEX

0.77

didSet

0.74

viewDidLoad

0.74

حياته

0.73

?>>

0.72

Personendaten

0.70

 initComponents

0.69

LayoutConstraint

0.68

Activations Density 0.017%

programming-related keywords and annotations

No Comments

No Known Activations