INDEX

Explanations

function definitions and invocations 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 @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

</i>

-0.60

</u>

-0.59

\\

-0.55

PreferredItem

-0.53

"`

-0.53

-0.51

</b>

-0.51

vara

-0.51

chel

-0.51

POSITIVE LOGITS

 itſelf

1.03

 myſelf

0.91

 purpoſe

0.86

 Monfieur

0.86

 Diſ

0.83

 leſs

0.83

 raiſ

0.83

 ſmall

0.81

Efq

0.81

 Theſe

0.81

Activations Density 0.212%

function definitions and invocations in programming code

No Comments

No Known Activations