INDEX

Explanations

pronouns, possessive pronouns, and personal relationships in a text

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 lele

-1.46

 Keny

-1.35

 makro

-1.35

 pixabay

-1.34

hcm

-1.31

 Confe

-1.29

 kram

-1.29

 Augu

-1.28

mef

-1.27

 Telex

-1.27

POSITIVE LOGITS

 whom

0.71

<bos>

0.63

träglich

0.59

 mnie

0.58

Vielleicht

0.57

whom

0.56

сюда

0.53

 obicei

0.53

 come

0.53

Faites

0.52

Activations Density 0.599%

pronouns, possessive pronouns, and personal relationships in a text

No Comments

No Known Activations