INDEX

Explanations

mathematical or formulaic expressions related to statistical analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Theſe

-1.35

 myſelf

-1.33

 purpoſe

-1.31

 Reſ

-1.31

 Anſ

-1.29

 propOrder

-1.28

 Inſ

-1.24

ſy

-1.24

 leſs

-1.21

 becauſe

-1.21

POSITIVE LOGITS

1.01

</i>

0.92

</b>

0.88

</em>

0.86

0.85

</strong>

0.81

and

0.80

</sup>

0.79

Activations Density 0.264%

mathematical or formulaic expressions related to statistical analysis

No Comments

No Known Activations