INDEX

Explanations

question marks and phrases indicating confusion or inquiry

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

 compared

-1.78

([

-1.71

 Strip

-1.52

while

-1.51

rightarrow

-1.48

ocal

-1.47

front

-1.44

 Frontier

-1.42

 spots

-1.38

([@

-1.34

POSITIVE LOGITS

·¸

5.18

ĻĤ

5.18

Į

5.12

®

5.04

½

4.98

ŀ

4.97

↵

4.93

↵

4.93

↵↵

4.93

Activations Density 0.014%

question marks and phrases indicating confusion or inquiry

No Comments

No Known Activations