INDEX

Explanations

references to a specific brand or product

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

New Auto-Interp

Configuration

ctigges/pythia-70m-deduped__res-sm_processed/2-res-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_resid_post

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

£

-1.88

hift

-1.85

µ

-1.81

¶

-1.79

Ĥ

-1.72

Ķ

-1.68

ĥ½

-1.65

Ĩ

-1.65

achus

-1.65

¼

-1.56

POSITIVE LOGITS

cks

1.78

ney

1.74

 cosa

1.67

rokee

1.57

neys

1.57

vy

1.56

apest

1.55

 Activities

1.54

arts

1.50

INFO

1.50

Activations Density 0.153%

references to a specific brand or product

No Comments

No Known Activations