INDEX

Explanations

code snippets related to programming logic and function definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rungsseite

-0.89

 kasarigan

-0.75

 propOrder

-0.75

AddTagHelper

-0.71

MLLoader

-0.70

 يتيمه

-0.69

MemoryWarning

-0.67

 <<<<<<<<<<<<<<

-0.66

RegressionTest

-0.65

RenderAtEndOf

-0.65

POSITIVE LOGITS

gotoxy

0.40

Console

0.35

Printf

0.34

UpdateCommand

0.31

 guys

0.31

Terminal

0.31

 Console

0.30

lanterna

0.30

 ישראל

0.30

console

0.29

Activations Density 0.336%

code snippets related to programming logic and function definitions

No Comments

No Known Activations