INDEX

Explanations

nothing of significance; it shows no activation for any terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 Meksiku

-0.83

TintMode

-0.77

----</

-0.68

oredCriteria

-0.61

ulemon

-0.61

ArrowToggle

-0.57

CopyWith

-0.57

arot

-0.55

windowFixed

-0.55

Šaltiniai

-0.55

POSITIVE LOGITS

 CreateTagHelper

0.60

 ExecuteAsync

0.52

tagHelperRunner

0.48

INPUTS

0.47

 ***!

0.47

ViewFeatures

0.46

 hObject

0.46

 kazi

0.44

 ModelExpression

0.44

ťaž

0.44

Activations Density 0.130%

nothing of significance; it shows no activation for any terms

No Comments

No Known Activations