INDEX

Explanations

references to various types of accidents

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

ĥ½

-1.52

¹

-1.43

OH

-1.37

dk

-1.31

 Supreme

-1.30

 answer

-1.29

↵

-1.28

↵↵

-1.28

POSITIVE LOGITS

 scenes

1.76

theless

1.57

arial

1.53

imet

1.47

proof

1.46

 areas

1.43

 periods

1.42

igraph

1.42

table

1.42

ulated

1.41

Activations Density 0.017%

references to various types of accidents

No Comments

No Known Activations