INDEX

Explanations

phrases that indicate results and conclusions from studies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

FINE

-0.51

enumi

-0.51

 prohibit

-0.45

 corresponding

-0.45

вець

-0.45

 kamen

-0.45

 ordini

-0.45

Fine

-0.43

ủi

-0.43

úrate

-0.41

POSITIVE LOGITS

astéroïdes

0.77

tagHelperRunner

0.74

 disambiguazione

0.72

 kasarigan

0.72

 ujednoznacz

0.71

 HttpNotFound

0.71

IGraphics

0.71

Semoga

0.69

 NSCoder

0.68

InputBorder

0.67

Activations Density 0.258%

phrases that indicate results and conclusions from studies

No Comments

No Known Activations