INDEX

Explanations

Twitter usernames and related text content

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

 gaily

-1.06

 unspeak

-1.01

 endeavouring

-0.95

 impelled

-0.92

 reconno

-0.90

 intrigu

-0.87

 vainly

-0.87

 tolerably

-0.83

 apprehen

-0.83

 unceasing

-0.81

POSITIVE LOGITS

 Wikiquote

0.67

 soggior

0.64

ostante

0.61

 garantis

0.60

MENAFN

0.56

 Wikisource

0.56

 incontr

0.56

 affez

0.56

 auguri

0.56

 sedia

0.56

Activations Density 0.054%

Twitter usernames and related text content

No Comments

No Known Activations