INDEX

Explanations

elements related to user interactions and programming syntax

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

exitRule

-0.60

 transfieras

-0.54

errHandler

-0.53

 CreateTagHelper

-0.52

principalTable

-0.51

AddTagHelper

-0.50

 Taktlose

-0.50

 intptr

-0.49

 gesunde

-0.49

 Wikiseite

-0.49

POSITIVE LOGITS

 assimilation

0.46

ans

0.40

 mone

0.39

 render

0.38

FON

0.38

rot

0.38

 interpretation

0.38

 decoding

0.38

 Interaction

0.37

 interpretations

0.37

Activations Density 1.023%

elements related to user interactions and programming syntax

No Comments

No Known Activations