INDEX

Explanations

references to extreme or exaggerated phenomena, often with a humorous or sarcastic tone

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

chanind/openwebtext-gemma

Features

16,384

Data Type

float32

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

ctigges/openwebtext-gemma-1024-cl

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-2.15

/***

-0.83

 minimalis

-0.81

 handels

-0.73

 stoff

-0.72

ⓧ

-0.70

 republi

-0.68

 geograf

-0.68

 konkre

-0.68

 verle

-0.67

POSITIVE LOGITS

 unlaw

1.05

 ecru

1.02

 impractica

0.99

 paradiso

0.98

 swarovski

0.95

 friable

0.91

 venuto

0.91

 liberality

0.91

 cioc

0.90

 soggior

0.88

Activations Density 1.445%

references to extreme or exaggerated phenomena, often with a humorous or sarcastic tone

No Comments

No Known Activations