INDEX

Explanations

phrases indicating personal relationships and emotional connections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

erdo

-0.57

 searches

-0.55

JspWriter

-0.49

 excl

-0.48

 tickets

-0.48

 newBuilder

-0.48

 تانيه

-0.48

 endwhile

-0.48

 doInBackground

-0.48

 againſt

-0.47

POSITIVE LOGITS

 acceptance

1.37

 accepting

1.27

 Acceptance

1.25

acceptance

1.21

Receiving

1.21

 Accepting

1.21

accept

1.17

 accept

1.16

 réception

1.14

 Receiving

1.12

Activations Density 0.318%

phrases indicating personal relationships and emotional connections

No Comments

No Known Activations