INDEX

Explanations

personal names and titles related to individuals

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

setVerticalGroup

-0.74

typeparam

-0.66

 CreateTagHelper

-0.61

 AssemblyCulture

-0.58

RenderAtEndOf

-0.56

RectangleBorder

-0.55

 ComVisible

-0.51

edoc

-0.49

yntaxException

-0.49

 aside

-0.47

POSITIVE LOGITS

 <>",

0.65

rungsseite

0.55

 semesters

0.55

 Pius

0.52

buah

0.50

IsPostBack

0.50

 FALLS

0.50

 screenshots

0.49

enderal

0.49

PSC

0.49

Activations Density 0.074%

personal names and titles related to individuals

No Comments

No Known Activations