INDEX

Explanations

word forms related to specific periods of time 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 effe

-1.09

 inder

-0.99

fte

-0.97

 compen

-0.97

 „,

-0.97

 dispen

-0.96

 doman

-0.95

mef

-0.95

 nece

-0.95

 ofre

-0.95

POSITIVE LOGITS

 sixties

0.58

 Soviet

0.57

 polio

0.57

mistak

0.55

era

0.54

 USSR

0.54

eniendo

0.52

 decades

0.52

 Beatles

0.52

agissait

0.52

Activations Density 0.360%

word forms related to specific periods of time and historical events

No Comments

No Known Activations