INDEX

Explanations

instances of the word "with."

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

New Auto-Interp

Configuration

ctigges/pythia-70m-deduped__mlp-sm_processed/2-mlp-sm

Prompts (Dashboard)

32,768 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

torch.float32

Hook Name

blocks.2.hook_mlp_out

Hook Layer

Architecture

standard

Context Size

128

Dataset

EleutherAI/the_pile_deduplicated

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 access

-1.60

ogen

-1.49

ocus

-1.44

vation

-1.36

 digest

-1.35

 read

-1.32

 participating

-1.31

amycin

-1.31

 dealing

-1.29

utz

-1.29

POSITIVE LOGITS

İ

2.43

ı

2.06

↵

2.05

↵↵

2.05

↵

2.05

č↵

2.05

<|outofrange|>

2.05

Activations Density 0.088%

instances of the word "with."

No Comments

No Known Activations