INDEX

Explanations

instances of names or references to places, especially in the context of social media or applications related to identity verification

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 Majefty

-0.72

]^{-

-0.69

 myſelf

-0.68

 ſtate

-0.67

ſelves

-0.67

 Anſ

-0.67

 itſelf

-0.66

ſelf

-0.65

 purpoſe

-0.64

úsqueda

-0.64

POSITIVE LOGITS

za

0.53

se

0.53

da

0.51

sa

0.49

 linkovi

0.46

 jakim

0.46

ja

0.45

0.44

 ostavi

0.44

đ

0.43

Activations Density 0.047%

instances of names or references to places, especially in the context of social media or applications related to identity verification

No Comments

No Known Activations