INDEX

Explanations

actions that indicate leadership or influence

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

XS

-1.53

)].

-1.49

 fain

-1.47

 relapse

-1.46

falls

-1.43

 lysis

-1.41

urop

-1.40

 spot

-1.40

?”

-1.38

oured

-1.36

POSITIVE LOGITS

»¿

2.02

 books

1.68

½

1.66

¤

1.62

smith

1.62

nier

1.60

³

1.59

ı

1.55

±

1.54

ity

1.51

Activations Density 0.384%

actions that indicate leadership or influence

No Comments

No Known Activations