INDEX

Explanations

code-related terms and components

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

ľĵ

-1.73

ŀ

-1.49

punk

-1.37

§

-1.36

uple

-1.34

·

-1.33

ļ

-1.32

 kick

-1.30

psin

-1.30

Ĥ¬

-1.25

POSITIVE LOGITS

ings

1.58

liography

1.54

journals

1.49

ncbi

1.48

 families

1.46

STA

1.44

:**

1.39

artments

1.37

usalem

1.37

BH

1.37

Activations Density 3.850%

code-related terms and components

No Comments

No Known Activations