INDEX

Explanations

technical keywords and structures related to programming and data definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

UseVisualStyle

-0.50

localctx

-0.49

 оригіналу

-0.36

énario

-0.36

 Ressources

-0.36

 poffible

-0.36

quinta

-0.34

 soli

-0.34

 clar

-0.34

 finger

-0.34

POSITIVE LOGITS

parsedMessage

0.64



0.59

 CreateTagHelper

0.56

fromnode

0.56

RenderAtEndOf

0.56

RTEE

0.55

 GenerationType

0.54

.*")]

0.52

 intptr

0.51

SourceChecksum

0.49

Activations Density 0.696%

technical keywords and structures related to programming and data definitions

No Comments

No Known Activations