INDEX

Explanations

references to administrative roles or functions

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

 true

-1.56

 lower

-1.53

opy

-1.51

 Eastern

-1.45

me

-1.43

 immediate

-1.43

UNC

-1.42

nger

-1.42

FORE

-1.41

opic

-1.40

POSITIVE LOGITS

isters

2.37

hel

1.99

ister

1.92

istar

1.84

helf

1.74

istry

1.73

»

1.71

dom

1.68

era

1.63

quist

1.61

Activations Density 0.006%

references to administrative roles or functions

No Comments

No Known Activations