INDEX

Explanations

sentences related to adding content and interacting with online platforms

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>

-2.49

BufferException

-0.89

CPtr

-0.75

 Wikimedijinoj

-0.74

illots

-0.73

endwhile

-0.73

CreateIndex

-0.73

runApp

-0.72

HasColumnType

-0.72

UnitTesting

-0.72

POSITIVE LOGITS

 maneu

2.59

 reluct

2.52

 impra

2.51

 affor

2.45

 increa

2.45

 encomp

2.43

 shenan

2.41

 disagre

2.38

 inev

2.37

 accla

2.36

Activations Density 0.444%

sentences related to adding content and interacting with online platforms

No Comments

No Known Activations