INDEX

Explanations

phrases related to specific dates, names, locations, and historical events

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

HuggingFaceFW/fineweb

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-3.47

ⓧ

-0.76

 découvre

-0.70

///**

-0.68

 préfère

-0.64

<?

-0.63

-0.62

//----

-0.61

//---

-0.61

 ressemble

-0.61

POSITIVE LOGITS

 véhic

1.12

 catég

1.04

 soulign

1.04

 conflic

1.00

 considér

0.99

 sappi

0.97

 marea

0.96

 unlaw

0.95

 valencia

0.95

 délib

0.94

Activations Density 1.178%

phrases related to specific dates, names, locations, and historical events

No Comments

No Known Activations