INDEX

Explanations

technical terms and references related to software development and libraries

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

 ModelExpression

-0.81

 AssemblyTitle

-0.74

AddTagHelper

-0.69

providedIn

-0.60

 AssemblyCulture

-0.58

yntaxException

-0.55

httphttps

-0.54

RenderAtEndOf

-0.54

MessageTagHelper

-0.53

IsContent

-0.51

POSITIVE LOGITS

BagLayout

0.44

 Mess

0.39

 RANK

0.39

Cam

0.39

YET

0.39

mybatisplus

0.39

 clinical

0.38

 deleteUser

0.38

thello

0.38

 magist

0.37

Activations Density 0.050%

technical terms and references related to software development and libraries

No Comments

No Known Activations