INDEX

Explanations

phrases discussing reasons or causes

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

 parteci

-0.88

 rispond

-0.72

 honn

-0.72

 espri

-0.70

 doveva

-0.70

 notare

-0.69

 veniva

-0.68

 sembrano

-0.68

 prosegu

-0.67

 dovrebbero

-0.66

POSITIVE LOGITS

 including

1.01

including

0.84

 Including

0.84

 ranging

0.81

Including

0.73

ranging

0.67

 different

0.66

包括

0.65

 INCLUDING

0.65

 besides

0.62

Activations Density 0.431%

phrases discussing reasons or causes

No Comments

No Known Activations