INDEX

Explanations

terms related to transformations in programming and data manipulation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 IUPAC

-0.70

roveň

-0.66

 lâmpada

-0.66

 nargin

-0.66

RSI

-0.66

 Pyle

-0.65

 areia

-0.64

SequentialGroup

-0.64

ícios

-0.64

kPa

-0.63

POSITIVE LOGITS

transform

3.12

 transform

3.07

Transform

2.87

 Transform

2.85

 transforms

2.58

 transformation

2.52

TRANSFORM

2.43

 TRANSFORM

2.41

 transforming

2.39

 transformations

2.38

Activations Density 0.077%

terms related to transformations in programming and data manipulation

No Comments

No Known Activations