INDEX

Explanations

terms related to predictions and future estimates

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

 reputation

-1.68

ansen

-1.64

pshire

-1.50

rsquo

-1.49

aird

-1.48

kered

-1.45

lor

-1.43

---|---

-1.37

ison

-1.35

icates

-1.35

POSITIVE LOGITS

pic

1.63

pic

1.43

1.40

 onto

1.35

[]

1.31

 wrong

1.27

posing

1.26

 slit

1.25

 gaps

1.25

ifle

1.24

Activations Density 0.008%

terms related to predictions and future estimates

No Comments

No Known Activations