INDEX

Explanations

instances of the word "interference" and its variants 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.10.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

chanind/openwebtext-gemma

Features

16,384

Data Type

float32

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

ctigges/openwebtext-gemma-1024-cl

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-2.50

País

-0.65

album

-0.63

public

-0.63

pub

-0.62

Comun

-0.61

 earn

-0.60

aplic

-0.60

eb

-0.58

Ду

-0.58

POSITIVE LOGITS

 paradiso

1.47

 stockholm

1.47

 Interference

1.42

 bandung

1.40

 ecru

1.39

 toledo

1.33

 riviera

1.32

 Minang

1.31

 Intere

1.30

 santiago

1.29

Activations Density 0.065%

instances of the word "interference" and its variants in various contexts

No Comments

No Known Activations