INDEX

Explanations

the word "simply" and its variations indicating straightforwardness or ease

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

Ģ

-1.83

robe

-1.74

Ĥ¬

-1.69

ļ

-1.65

Ĭ

-1.64

ĨĴ

-1.56

ħ

-1.52

Ĳ

-1.51

phrine

-1.49

 brightest

-1.48

POSITIVE LOGITS

bling

1.58

zet

1.57

reb

1.56

format

1.56

cciÃ³n

1.56

gone

1.48

ismus

1.38

 exchanges

1.32

bent

1.30

itet

1.30

Activations Density 0.026%

the word "simply" and its variations indicating straightforwardness or ease

No Comments

No Known Activations