INDEX

Explanations

instances of the word "graphic" or its derivatives

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

§

-2.77

ĨĴ

-2.26

Ĳ

-2.20

´

-2.19

¸

-2.15

¨

-2.15

Ĥ¬

-2.11

Ļª

-2.10

©

-2.05

Ĵ

-2.03

POSITIVE LOGITS

smallcaps

1.79

ulated

1.77

card

1.69

"}](#

1.65

fault

1.65

fon

1.63

oon

1.60

{"

1.59

ulator

1.57

ulation

1.54

Activations Density 0.012%

instances of the word "graphic" or its derivatives

No Comments

No Known Activations