INDEX

Explanations

words related to the concept of attracting or being attracted to something

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>

-3.15

Vegeu

-0.86

ⓧ

-0.86

Referencer

-0.68

PutMapping

-0.68

/***

-0.67

SizeMode

-0.63

glMatrixMode

-0.62

Fordítás

-0.62

estacks

-0.62

POSITIVE LOGITS

 lele

1.51

 stockholm

1.51

 wien

1.49

 meis

1.46

aen

1.42

 thut

1.39

mef

1.37

 riva

1.36

 uniqu

1.35

vry

1.34

Activations Density 0.120%

words related to the concept of attracting or being attracted to something

No Comments

No Known Activations