INDEX

Explanations

references to employers and various types of objects or items, particularly in legal and product contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

setObjectName

-0.51

 AssemblyCulture

-0.50

TextSpan

-0.50

Ecotoxicity

-0.48

 veneer

-0.46

IFO

-0.46

 veneers

-0.45

 tamu

-0.45

#+#

-0.44

φέρει

-0.43

POSITIVE LOGITS

stdc

0.64

RenderAtEndOf

0.63

bootstrapcdn

0.60

0.59

 насељу

0.58

rebbero

0.57

 كومونز

0.54

orianCalendar

0.53

 accompanying

0.53

 counting

0.52

Activations Density 0.754%

references to employers and various types of objects or items, particularly in legal and product contexts

No Comments

No Known Activations