INDEX

Explanations

mathematical notation and formal definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

прочем

-0.58

 respons

-0.51

 Emphas

-0.50

++);

-0.48

&)

-0.46

摩

-0.46

 traz

-0.45

iy

-0.44

 bezeichneter

-0.43

*}{

-0.43

POSITIVE LOGITS

 there

0.90

InjectAttribute

0.81

 esistono

0.79

either

0.78

Either

0.78

 esiste

0.77

 Either

0.77

 either

0.75

 CreateTagHelper

0.75

 существует

0.73

Activations Density 1.491%

mathematical notation and formal definitions

No Comments

No Known Activations