INDEX

Explanations

terms related to the concept of localization or being situated in a specific place

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

oscopic

-1.54

ubicin

-1.52

rocy

-1.44

walks

-1.42

aceae

-1.40

 whales

-1.40

ful

-1.34

rely

-1.33

oxacin

-1.33

olic

-1.32

POSITIVE LOGITS

itÃ©s

1.70

ement

1.63

(\<

1.54

ence

1.48

(\>

1.45

ently

1.43

iencies

1.43

 supra

1.41

positions

1.41

izer

1.40

Activations Density 0.019%

terms related to the concept of localization or being situated in a specific place

No Comments

No Known Activations