INDEX

Explanations

places or locations

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>

-2.06

 serve

-0.78

 assume

-0.78

//

-0.77

 interact

-0.77

 provide

-0.76

 continue

-0.75

 establish

-0.75

put

-0.75

protected

-0.75

POSITIVE LOGITS

Juf

2.49

 affor

2.42

 impra

2.29

 sovere

2.27

 accla

2.26

 maneu

2.25

 depic

2.24

 Intere

2.23

 emphat

2.21

 squa

2.20

Activations Density 1.088%

places or locations

No Comments

No Known Activations