INDEX

Explanations

function definitions and assignments in coding contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 CreateTagHelper

-0.55

BufferException

-0.49

rrggbb

-0.45

afficheront

-0.43

VersionUID

-0.42

 iprot

-0.40

RenderAtEndOf

-0.40

望

-0.39

webElementXpaths

-0.39

NameInMap

-0.38

POSITIVE LOGITS

 jsPsych

0.52

 geschikt

0.40

 Matos

0.39

 stratégies

0.38

 ComVisible

0.37

 cible

0.37

 belangrij

0.36

吞

0.36

RegressionTest

0.35

ķ

0.35

Activations Density 0.503%

function definitions and assignments in coding contexts

No Comments

No Known Activations