INDEX

Explanations

evaluations of satisfaction or well-being within various contexts

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

 religieuse

-0.57

 végétale

-0.56

 altrett

-0.55

󠁧

-0.55

 latine

-0.52

tabular

-0.50

 boats

-0.49

 nevo

-0.49

 câte

-0.49

 dentaire

-0.49

POSITIVE LOGITS

BeginInit

0.83

 незавершена

0.82

 resourceCulture

0.80

ніципалі

0.80

ThroughAttribute

0.76

]")]

0.76

:✨

0.75

culously

0.73

SuspendLayout

0.69

AutoScaleMode

0.69

Activations Density 1.069%

evaluations of satisfaction or well-being within various contexts

No Comments

No Known Activations