INDEX

Explanations

discriminatory language related to sexual orientation, gender identity, and civil rights

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

 fays

-0.72

 feen

-0.70

 endom

-0.70

Juf

-0.67

 fign

-0.66

 Pfal

-0.63

 Dés

-0.63

fua

-0.62

 fince

-0.62

 sonne

-0.61

POSITIVE LOGITS

<bos>

0.64

SneakyThrows

0.62

nationality

0.56

niająca

0.53

üedad

0.52

KELEY

0.49

Fitment

0.48

 agences

0.48

pañas

0.48

 Walkover

0.47

Activations Density 0.291%

discriminatory language related to sexual orientation, gender identity, and civil rights

No Comments

No Known Activations