INDEX

Explanations

phrases indicating roles or relationships within organizations or groups

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

inSlope

-0.50

AddTagHelper

-0.49

BeginContext

-0.49

TIA

-0.44

ValueGeneration

-0.43

Према

-0.42

SPC

-0.42

CPD

-0.41

Tia

-0.40

Tia

-0.40

POSITIVE LOGITS

StoryboardSegue

0.48

 levier

0.41

RemoveField

0.41

 participate

0.40

 participation

0.40

 partici

0.40

参与

0.39

antMatchers

0.38

 udział

0.38

tagext

0.38

Activations Density 0.319%

phrases indicating roles or relationships within organizations or groups

No Comments

No Known Activations