INDEX

Explanations

identifiers and parameters related to modules and processes in a programming context

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

">//

-0.51

gel

-0.43

ÉR

-0.42

скоп

-0.42

th

-0.42

 Beal

-0.41

 Assisted

-0.41

Mow

-0.41

uz

-0.41

 moderate

-0.41

POSITIVE LOGITS

日閲覧

0.98

 مشين

0.84

 Roskov

0.84

 CreateTagHelper

0.81

principalColumn

0.77

Efq

0.77

PreferredItem

0.76

ArgsConstructor

0.75

 resourceCulture

0.74

 gynhyrchwyd

0.73

Activations Density 0.361%

identifiers and parameters related to modules and processes in a programming context

No Comments

No Known Activations