INDEX

Explanations

mentions of LGBTQ+ related terms and discrimination issues

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 corrom

-0.54

 huma

-0.49

 dépens

-0.48

 engend

-0.48

 peup

-0.47

CodedInputStream

-0.46

 vulga

-0.45

 dépass

-0.45

 répand

-0.45

 palab

-0.44

POSITIVE LOGITS

 trecut

0.58

dă

0.54

 disambiguazione

0.52

 Audiodateien

0.51

 blest

0.51

SBATCH

0.51

üedad

0.50

 împre

0.49

jectures

0.49

 disqual

0.49

Activations Density 0.394%

mentions of LGBTQ+ related terms and discrimination issues

No Comments

No Known Activations