INDEX

Explanations

names of people and their affiliations or activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

HasForeignKey

-0.60

NUMX

-0.60

Życiorys

-0.60

BrowserModule

-0.58

ArrowToggle

-0.58

 förb

-0.57

 tối

-0.57

StoreMessageInfo

-0.57

 Daarom

-0.56

jería

-0.55

POSITIVE LOGITS

 respectively

0.76

それぞれ

0.69

respectively

0.64

 allemaal

0.59

 nahilalakip

0.58

each

0.56

MLLoader

0.55

 were

0.54

featureID

0.54

+#+

0.53

Activations Density 0.284%

names of people and their affiliations or activities

No Comments

No Known Activations