INDEX

Explanations

words related to online dating services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

makeText

-0.57

CppMethod

-0.57

AutoScaleMode

-0.57

EndInit

-0.54

enderror

-0.54

RetentionPolicy

-0.53

mphony

-0.53

geten

-0.52

ricians

-0.52

testcase

-0.52

POSITIVE LOGITS

 dating

1.64

 Dating

1.44

Dating

1.39

 matchmaking

1.38

dating

1.30

 Tinder

1.29

 Match

1.15

 matching

1.12

 date

1.09

 match

1.09

Activations Density 0.137%

words related to online dating services

No Comments

No Known Activations