INDEX

Explanations

strong emotional statements and accusations involving individuals or groups

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

 Kategor

-0.56

fjspx

-0.56

 kosme

-0.56

 minimalis

-0.56

İstinadlar

-0.53

 bunda

-0.52

 protokol

-0.51

NewRow

-0.50

basicConfig

-0.49

DbType

-0.49

POSITIVE LOGITS

 yourselves

1.13

 yourself

1.07

yourself

0.97

 Yourself

0.94

 embodi

0.80

 YOURSELF

0.80

 youre

0.80

 your

0.77

Yourself

0.76

 resear

0.75

Activations Density 0.653%

strong emotional statements and accusations involving individuals or groups

No Comments

No Known Activations