INDEX

Explanations

references to the letter 'Z' in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

ModelSerializer

-0.77

AnchorStyles

-0.65

 faſt

-0.61

 المعيارى

-0.61

 pleaſure

-0.61

($__

-0.60

SOUNDBITE

-0.58

发表于

-0.57

 lenker

-0.57

 שוליים

-0.57

POSITIVE LOGITS

 kasarigan

0.56

0.53

0.51

PathVariable

0.50

 qualifié

0.49

 automáticamente

0.48

callable

0.48

idable

0.48

tahankan

0.47

lancer

0.46

Activations Density 0.109%

references to the letter 'Z' in various contexts

No Comments

No Known Activations