INDEX

Explanations

technical terms and phrases related to software application and government support

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>

-2.08

ברס

-0.63

public

-0.62

ret

-0.61

ӱ

-0.60

ּ

-0.60

char

-0.59

file

-0.59

 trim

-0.59

module

-0.59

POSITIVE LOGITS

 reluct

1.56

 increa

1.52

 madonna

1.52

 maneu

1.49

 stockholm

1.46

 impra

1.45

 strick

1.44

 lidl

1.42

 disagre

1.41

 shenan

1.41

Activations Density 1.509%

technical terms and phrases related to software application and government support

No Comments

No Known Activations