INDEX

Explanations

occurrences of the word "manual" in various contexts

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>

-2.18

enumerate

-0.55

 transform

-0.55

 share

-0.54

宿

-0.54

transform

-0.53

 Smith

-0.52

 collaborate

-0.52

/*++

-0.52

<?

-0.51

POSITIVE LOGITS

 MANUAL

1.16

 Minang

1.15

 Manuals

1.13

 Manual

1.13

 manual

1.10

Manual

1.07

 Compañ

1.06

 ecru

1.05

 manuals

1.04

 Augu

1.00

Activations Density 0.059%

occurrences of the word "manual" in various contexts

No Comments

No Known Activations