INDEX

Explanations

references to accuracy and evaluations in various contexts

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

principalColumn

-0.53

Diweddarwch

-0.50

 Infórmanos

-0.49

 AssemblyCompany

-0.48

ThroughAttribute

-0.46

ביוגרפיה

-0.46

AndEndTag

-0.46

IntoConstraints

-0.45

 فريبيس

-0.45

BufferException

-0.45

POSITIVE LOGITS

 հղումներ

0.47

 pprint

0.45

 diagnosis

0.42

 comment

0.42

 TextAlign

0.41

casian

0.41

stringstream

0.39

 StringTokenizer

0.39

 OMITBAD

0.39

 summary

0.39

Activations Density 2.469%

references to accuracy and evaluations in various contexts

No Known Activations