INDEX

Explanations

sentences that indicate key points in a structured discussion or report

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

Viitteet

-0.73

 TextInputType

-0.66

 consultato

-0.64

 Cæsar

-0.62

"):

-0.61

″]

-0.61

Epil

-0.61

 createSprite

-0.60

anso

-0.59

POSITIVE LOGITS

ConstraintMaker

0.54

labelledby

0.49

But

0.48

but

0.43

 However

0.43

 било

0.42

0.41

So

0.41

endiri

0.41

 Obviously

0.40

Activations Density 0.915%

sentences that indicate key points in a structured discussion or report

No Comments

No Known Activations