INDEX

Explanations

terms related to neuroscience and neurochemistry

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Configuration

ctigges/pythia-70m-deduped__res-sm_processed/2-res-sm

Prompts (Dashboard)

32,768 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

torch.float32

Hook Name

blocks.2.hook_resid_post

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

river

-1.67

aucoup

-1.59

irection

-1.56

emente

-1.53

uant

-1.51

nÃ©e

-1.46

 contrary

-1.45

orget

-1.44

 dont

-1.43

 oÃ¹

-1.41

POSITIVE LOGITS

Ĥ

3.26

ģ

3.25

·¸

3.19

ħ

3.19

ĭ

3.02

¾

3.00

Ħ

2.98

²

2.92

Ĩ

2.91

±

2.88

Activations Density 0.053%

terms related to neuroscience and neurochemistry

No Comments

No Known Activations