INDEX

Explanations

questions and inquiries about technical understanding or troubleshooting

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

 Roskov

-0.49

wahati

-0.39

 Houſe

-0.38

 houſe

-0.38

 مشين

-0.36

lesias

-0.36

Enumeration

-0.35

 againſt

-0.35

 ſtand

-0.34

 skolan

-0.34

POSITIVE LOGITS

ModelAdmin

0.54

发表于

0.53

httphttps

0.51

 surla

0.51

 referrerpolicy

0.49

sizeCache

0.47

webElementGuid

0.47

transQ

0.46

 Tail

0.45

 Occur

0.45

Activations Density 0.130%

questions and inquiries about technical understanding or troubleshooting

No Comments

No Known Activations