INDEX

Explanations

topics related to the wild, such as animals, nature, or wilderness

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-3.55

addComponent

-0.91

CreateIndex

-0.86

HasColumnType

-0.83

HasIndex

-0.83

ValueGenerated

-0.82

put

-0.81

item

-0.81

put

-0.80

he

-0.80

POSITIVE LOGITS

 affor

2.47

Juf

2.47

 increa

2.46

 maneu

2.35

 stockholm

2.34

 lidl

2.30

 emphat

2.30

 madonna

2.29

 effe

2.27

ftu

2.26

Activations Density 0.079%

topics related to the wild, such as animals, nature, or wilderness

No Comments

No Known Activations