INDEX

Explanations

instances of the word "through" and its variations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.12.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

torch.float32

Hook Point

blocks.12.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>

-1.26

fetch

-0.57

Cal

-0.57

cal

-0.56

et

-0.55

Cal

-0.54

POSITIVE LOGITS

 napoli

1.20

 outlander

1.17

 soggior

1.15

 venuto

1.11

 peugeot

1.08

 tramont

1.08

 paradiso

1.07

 cioc

1.07

 conflic

1.07

 dovr

1.06

Activations Density 0.136%

instances of the word "through" and its variations

No Comments

No Known Activations