INDEX

Explanations

references to specific card names in a card game

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

 kasarigan

-0.72

Autoritní

-0.70

sightly

-0.67

 autorytatywna

-0.66

 darbu

-0.64

wavering

-0.64

relenting

-0.62

 constate

-0.59

 ExecuteAsync

-0.59

الدراسه

-0.58

POSITIVE LOGITS

 ardu

0.67

 snoopy

0.65

 pessi

0.63

 strick

0.62

 finn

0.62

 laun

0.62

 :)))

0.61

 XNUMX

0.61

↔

0.61

 Malte

0.60

Activations Density 0.111%

references to specific card names in a card game

No Comments

No Known Activations