INDEX

Explanations

Phrases or statements that include the word "through"

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>

-3.12

<?

-0.75

ⓧ

-0.74

/***

-0.69

/*

-0.68

-0.63

<?

-0.63

ask

-0.63

 meet

-0.61

 decide

-0.61

POSITIVE LOGITS

 soulign

1.38

 Khart

1.33

 riviera

1.32

 napoli

1.30

Juf

1.29

 maroc

1.29

 stockholm

1.24

 eiffel

1.23

 roul

1.23

 affor

1.23

Activations Density 0.177%

Phrases or statements that include the word "through"

No Comments

No Known Activations