INDEX

Explanations

references to the word "Smart"

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

New Auto-Interp

Configuration

ctigges/pythia-70m-deduped__mlp-sm_processed/0-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.0.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

 darker

-1.54

 warmer

-1.53

its

-1.51

versions

-1.50

 abusive

-1.46

 spite

-1.38

 innocence

-1.36

 inevitable

-1.35

'</

-1.34

 poorer

-1.33

POSITIVE LOGITS

ĻĤ

2.34

ģ

2.23

ĸ

2.21

Ł

2.19

stown

2.08

Ĵ

2.06

ķ

2.03

Ħ

2.02

ª

1.85

±

1.85

Activations Density 0.015%

references to the word "Smart"

No Comments

No Known Activations