INDEX

Explanations

terms related to confirmation and verification processes

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

 reac

-0.47

Aktualisiert

-0.46

 climático

-0.43

 otomatig

-0.43

 uintptr

-0.42

AutoField

-0.42

enment

-0.42

HtmlAttribute

-0.41

tagHelperRunner

-0.40

siella

-0.39

POSITIVE LOGITS

 détru

0.64

 Hist

0.60

)!=

0.59

 getOrder

0.57

 vérit

0.57

 jspb

0.56

 Noire

0.54

 citoy

0.54

 snippetHide

0.54

 condamné

0.54

Activations Density 0.084%

terms related to confirmation and verification processes

No Comments

No Known Activations