INDEX

Explanations

structured references or tables in the text

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

 Wikiseite

-0.56

usepackage

-0.54

attutto

-0.53

////////////////

-0.51

Derbyniad

-0.50

cadilly

-0.46

basicConfig

-0.46

Begriffsklä

-0.45

urlpatterns

-0.44

queles

-0.44

POSITIVE LOGITS

0.50

RectangleBorder

0.50

0.49

httphttps

0.45

 nakalista

0.45

tagHelperRunner

0.43

Activations Density 0.721%

structured references or tables in the text

No Comments

No Known Activations