INDEX

Explanations

structured lists and specific phases of training or procedures

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

ThroughAttribute

-0.56

MLLoader

-0.55

 CreateTagHelper

-0.54

الدراسه

-0.52

OGND

-0.48

TypedDataSet

-0.48

 незавершена

-0.47

 GenerationType

-0.47

jgl

-0.45

titem

-0.45

POSITIVE LOGITS

)]$

0.40

 This

0.38

})]

0.37

 Both

0.36

※

0.36

Ded

0.35

Notae

0.35

SharedDtor

0.35

This

0.35

?}",

0.35

Activations Density 0.151%

structured lists and specific phases of training or procedures

No Comments

No Known Activations