INDEX

Explanations

phrases that indicate functions and processes in programming or computing contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.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

-0.89

 Nowadays

-0.78

 equipments

-0.78

########.

-0.78

 resourceCulture

-0.74

 sufferings

-0.74

الحياه

-0.69

 Moreover

-0.69

Moreover

-0.68

Nowadays

-0.68

POSITIVE LOGITS

Whilst

0.68

 differing

0.64

 preventative

0.59

 whilst

0.59

atother

0.56

 Whilst

0.55

 incredibly

0.54

 essentially

0.54

tfrac

0.54

 necesitar

0.53

Activations Density 1.908%

phrases that indicate functions and processes in programming or computing contexts

No Comments

No Known Activations