INDEX

Explanations

terms related to algorithms and performance in data processing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

ISPR

-0.57

 nghề

-0.48

Gön

-0.48

CreateTable

-0.47

ècie

-0.47

umar

-0.47

 Humanos

-0.46

BURGH

-0.46

 manned

-0.45

 Timur

-0.44

POSITIVE LOGITS

 layer

0.84

 architecture

0.78

 समीक्षक

0.70

 Layer

0.69

 المعيارى

0.69

layer

0.68

 infrastructure

0.68

Referencie

0.66

 layers

0.66

Layer

0.65

Activations Density 0.872%

terms related to algorithms and performance in data processing

No Comments

No Known Activations