INDEX

Explanations

mentions of specific dates and historical events

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

 antik

-1.08

 keramik

-1.00

 seksi

-0.94

 kafe

-0.93

 kade

-0.93

erk

-0.92

lü

-0.92

 kooper

-0.90

 optik

-0.89

 bambu

-0.88

POSITIVE LOGITS

 impra

1.07

 intersper

1.05

 scrat

1.05

 depic

1.04

 shenan

1.03

 affor

1.01

 shewn

1.00

 cushi

1.00

 tolerably

1.00

 unspeak

0.98

Activations Density 0.121%

mentions of specific dates and historical events

No Comments

No Known Activations