INDEX

Explanations

function definitions and type annotations in programming code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.51

-0.49

-0.47

 free

-0.47

 Free

-0.44

-0.43

↵

-0.42

 libre

-0.42

But

-0.41

but

-0.40

POSITIVE LOGITS

 nahilalakip

1.24

 дописавши

1.05

########.

1.03

 myſelf

0.99

ſelves

0.96

WriteBarrier

0.95

setVerticalGroup

0.94

 pleaſure

0.94

 houſe

0.94

 defaultstate

0.93

Activations Density 0.061%

function definitions and type annotations in programming code

No Comments

No Known Activations