INDEX

Explanations

negative sentiments and statements of rejection

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.34.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

 ComVisible

-0.69

 autorytatywna

-0.64

 snippetHide

-0.57

IndentedString

-0.56

tagPool

-0.55

bootstrapcdn

-0.54

 Paglinawan

-0.54

perfectly

-0.53

MigrationBuilder

-0.52

oa̍t

-0.52

POSITIVE LOGITS

 tolerate

0.58

 tolerated

0.57

 tolerance

0.53

 pleasant

0.53

 toler

0.53

 acceptable

0.50

 toller

0.48

 conducive

0.47

прият

0.46

 EVER

0.45

Activations Density 0.381%

negative sentiments and statements of rejection

No Comments

No Known Activations